Skip to content

GitLab

Commit 62f68735 authored by laibao's avatar laibao
Browse files

No commit message 

No commit message
parents
Pipeline #1769 canceled with stages
Hide whitespace changes
Inline Side-by-side
Showing with 2263 additions and 0 deletions
benchmarks/sonnet.txt 0 → 100644
View file @ 62f68735
FROM fairest creatures we desire increase,
That thereby beauty's rose might never die,
But as the riper should by time decease,
His tender heir might bear his memory:
But thou, contracted to thine own bright eyes,
Feed'st thy light'st flame with self-substantial fuel,
Making a famine where abundance lies,
Thyself thy foe, to thy sweet self too cruel.
Thou that art now the world's fresh ornament
And only herald to the gaudy spring,
Within thine own bud buriest thy content
And, tender churl, makest waste in niggarding.
Pity the world, or else this glutton be,
To eat the world's due, by the grave and thee.
When forty winters shall beseige thy brow,
And dig deep trenches in thy beauty's field,
Thy youth's proud livery, so gazed on now,
Will be a tatter'd weed, of small worth held:
Then being ask'd where all thy beauty lies,
Where all the treasure of thy lusty days,
To say, within thine own deep-sunken eyes,
Were an all-eating shame and thriftless praise.
How much more praise deserved thy beauty's use,
If thou couldst answer 'This fair child of mine
Shall sum my count and make my old excuse,'
Proving his beauty by succession thine!
This were to be new made when thou art old,
And see thy blood warm when thou feel'st it cold.
Look in thy glass, and tell the face thou viewest
Now is the time that face should form another;
Whose fresh repair if now thou not renewest,
Thou dost beguile the world, unbless some mother.
For where is she so fair whose unear'd womb
Disdains the tillage of thy husbandry?
Or who is he so fond will be the tomb
Of his self-love, to stop posterity?
Thou art thy mother's glass, and she in thee
Calls back the lovely April of her prime:
So thou through windows of thine age shall see
Despite of wrinkles this thy golden time.
But if thou live, remember'd not to be,
Die single, and thine image dies with thee.
Unthrifty loveliness, why dost thou spend
Upon thyself thy beauty's legacy?
Nature's bequest gives nothing but doth lend,
And being frank she lends to those are free.
Then, beauteous niggard, why dost thou abuse
The bounteous largess given thee to give?
Profitless usurer, why dost thou use
So great a sum of sums, yet canst not live?
For having traffic with thyself alone,
Thou of thyself thy sweet self dost deceive.
Then how, when nature calls thee to be gone,
What acceptable audit canst thou leave?
Thy unused beauty must be tomb'd with thee,
Which, used, lives th' executor to be.
Those hours, that with gentle work did frame
The lovely gaze where every eye doth dwell,
Will play the tyrants to the very same
And that unfair which fairly doth excel:
For never-resting time leads summer on
To hideous winter and confounds him there;
Sap cheque'd with frost and lusty leaves quite gone,
Beauty o'ersnow'd and bareness every where:
Then, were not summer's distillation left,
A liquid prisoner pent in walls of glass,
Beauty's effect with beauty were bereft,
Nor it nor no remembrance what it was:
But flowers distill'd though they with winter meet,
Leese but their show; their substance still lives sweet.
Then let not winter's ragged hand deface
In thee thy summer, ere thou be distill'd:
Make sweet some vial; treasure thou some place
With beauty's treasure, ere it be self-kill'd.
That use is not forbidden usury,
Which happies those that pay the willing loan;
That's for thyself to breed another thee,
Or ten times happier, be it ten for one;
Ten times thyself were happier than thou art,
If ten of thine ten times refigured thee:
Then what could death do, if thou shouldst depart,
Leaving thee living in posterity?
Be not self-will'd, for thou art much too fair
To be death's conquest and make worms thine heir.
Lo! in the orient when the gracious light
Lifts up his burning head, each under eye
Doth homage to his new-appearing sight,
Serving with looks his sacred majesty;
And having climb'd the steep-up heavenly hill,
Resembling strong youth in his middle age,
yet mortal looks adore his beauty still,
Attending on his golden pilgrimage;
But when from highmost pitch, with weary car,
Like feeble age, he reeleth from the day,
The eyes, 'fore duteous, now converted are
From his low tract and look another way:
So thou, thyself out-going in thy noon,
Unlook'd on diest, unless thou get a son.
Music to hear, why hear'st thou music sadly?
Sweets with sweets war not, joy delights in joy.
Why lovest thou that which thou receivest not gladly,
Or else receivest with pleasure thine annoy?
If the true concord of well-tuned sounds,
By unions married, do offend thine ear,
They do but sweetly chide thee, who confounds
In singleness the parts that thou shouldst bear.
Mark how one string, sweet husband to another,
Strikes each in each by mutual ordering,
Resembling sire and child and happy mother
Who all in one, one pleasing note do sing:
Whose speechless song, being many, seeming one,
Sings this to thee: 'thou single wilt prove none.'
Is it for fear to wet a widow's eye
That thou consumest thyself in single life?
Ah! if thou issueless shalt hap to die.
The world will wail thee, like a makeless wife;
The world will be thy widow and still weep
That thou no form of thee hast left behind,
When every private widow well may keep
By children's eyes her husband's shape in mind.
Look, what an unthrift in the world doth spend
Shifts but his place, for still the world enjoys it;
But beauty's waste hath in the world an end,
And kept unused, the user so destroys it.
No love toward others in that bosom sits
That on himself such murderous shame commits.
For shame! deny that thou bear'st love to any,
Who for thyself art so unprovident.
Grant, if thou wilt, thou art beloved of many,
But that thou none lovest is most evident;
For thou art so possess'd with murderous hate
That 'gainst thyself thou stick'st not to conspire.
Seeking that beauteous roof to ruinate
Which to repair should be thy chief desire.
O, change thy thought, that I may change my mind!
Shall hate be fairer lodged than gentle love?
Be, as thy presence is, gracious and kind,
Or to thyself at least kind-hearted prove:
Make thee another self, for love of me,
That beauty still may live in thine or thee.
As fast as thou shalt wane, so fast thou growest
In one of thine, from that which thou departest;
And that fresh blood which youngly thou bestowest
Thou mayst call thine when thou from youth convertest.
Herein lives wisdom, beauty and increase:
Without this, folly, age and cold decay:
If all were minded so, the times should cease
And threescore year would make the world away.
Let those whom Nature hath not made for store,
Harsh featureless and rude, barrenly perish:
Look, whom she best endow'd she gave the more;
Which bounteous gift thou shouldst in bounty cherish:
She carved thee for her seal, and meant thereby
Thou shouldst print more, not let that copy die.
When I do count the clock that tells the time,
And see the brave day sunk in hideous night;
When I behold the violet past prime,
And sable curls all silver'd o'er with white;
When lofty trees I see barren of leaves
Which erst from heat did canopy the herd,
And summer's green all girded up in sheaves
Borne on the bier with white and bristly beard,
Then of thy beauty do I question make,
That thou among the wastes of time must go,
Since sweets and beauties do themselves forsake
And die as fast as they see others grow;
And nothing 'gainst Time's scythe can make defence
Save breed, to brave him when he takes thee hence.
O, that you were yourself! but, love, you are
No longer yours than you yourself here live:
Against this coming end you should prepare,
And your sweet semblance to some other give.
So should that beauty which you hold in lease
Find no determination: then you were
Yourself again after yourself's decease,
When your sweet issue your sweet form should bear.
Who lets so fair a house fall to decay,
Which husbandry in honour might uphold
Against the stormy gusts of winter's day
And barren rage of death's eternal cold?
O, none but unthrifts! Dear my love, you know
You had a father: let your son say so.
Not from the stars do I my judgment pluck;
And yet methinks I have astronomy,
But not to tell of good or evil luck,
Of plagues, of dearths, or seasons' quality;
Nor can I fortune to brief minutes tell,
Pointing to each his thunder, rain and wind,
Or say with princes if it shall go well,
By oft predict that I in heaven find:
But from thine eyes my knowledge I derive,
And, constant stars, in them I read such art
As truth and beauty shall together thrive,
If from thyself to store thou wouldst convert;
Or else of thee this I prognosticate:
Thy end is truth's and beauty's doom and date.
When I consider every thing that grows
Holds in perfection but a little moment,
That this huge stage presenteth nought but shows
Whereon the stars in secret influence comment;
When I perceive that men as plants increase,
Cheered and cheque'd even by the self-same sky,
Vaunt in their youthful sap, at height decrease,
And wear their brave state out of memory;
Then the conceit of this inconstant stay
Sets you most rich in youth before my sight,
Where wasteful Time debateth with Decay,
To change your day of youth to sullied night;
And all in war with Time for love of you,
As he takes from you, I engraft you new.
But wherefore do not you a mightier way
Make war upon this bloody tyrant, Time?
And fortify yourself in your decay
With means more blessed than my barren rhyme?
Now stand you on the top of happy hours,
And many maiden gardens yet unset
With virtuous wish would bear your living flowers,
Much liker than your painted counterfeit:
So should the lines of life that life repair,
Which this, Time's pencil, or my pupil pen,
Neither in inward worth nor outward fair,
Can make you live yourself in eyes of men.
To give away yourself keeps yourself still,
And you must live, drawn by your own sweet skill.
Who will believe my verse in time to come,
If it were fill'd with your most high deserts?
Though yet, heaven knows, it is but as a tomb
Which hides your life and shows not half your parts.
If I could write the beauty of your eyes
And in fresh numbers number all your graces,
The age to come would say 'This poet lies:
Such heavenly touches ne'er touch'd earthly faces.'
So should my papers yellow'd with their age
Be scorn'd like old men of less truth than tongue,
And your true rights be term'd a poet's rage
And stretched metre of an antique song:
But were some child of yours alive that time,
You should live twice; in it and in my rhyme.
Shall I compare thee to a summer's day?
Thou art more lovely and more temperate:
Rough winds do shake the darling buds of May,
And summer's lease hath all too short a date:
Sometime too hot the eye of heaven shines,
And often is his gold complexion dimm'd;
And every fair from fair sometime declines,
By chance or nature's changing course untrimm'd;
But thy eternal summer shall not fade
Nor lose possession of that fair thou owest;
Nor shall Death brag thou wander'st in his shade,
When in eternal lines to time thou growest:
So long as men can breathe or eyes can see,
So long lives this and this gives life to thee.
Devouring Time, blunt thou the lion's paws,
And make the earth devour her own sweet brood;
Pluck the keen teeth from the fierce tiger's jaws,
And burn the long-lived phoenix in her blood;
Make glad and sorry seasons as thou fleets,
And do whate'er thou wilt, swift-footed Time,
To the wide world and all her fading sweets;
But I forbid thee one most heinous crime:
O, carve not with thy hours my love's fair brow,
Nor draw no lines there with thine antique pen;
Him in thy course untainted do allow
For beauty's pattern to succeeding men.
Yet, do thy worst, old Time: despite thy wrong,
My love shall in my verse ever live young.
A woman's face with Nature's own hand painted
Hast thou, the master-mistress of my passion;
A woman's gentle heart, but not acquainted
With shifting change, as is false women's fashion;
An eye more bright than theirs, less false in rolling,
Gilding the object whereupon it gazeth;
A man in hue, all 'hues' in his controlling,
Much steals men's eyes and women's souls amazeth.
And for a woman wert thou first created;
Till Nature, as she wrought thee, fell a-doting,
And by addition me of thee defeated,
By adding one thing to my purpose nothing.
But since she prick'd thee out for women's pleasure,
Mine be thy love and thy love's use their treasure.
So is it not with me as with that Muse
Stirr'd by a painted beauty to his verse,
Who heaven itself for ornament doth use
And every fair with his fair doth rehearse
Making a couplement of proud compare,
With sun and moon, with earth and sea's rich gems,
With April's first-born flowers, and all things rare
That heaven's air in this huge rondure hems.
O' let me, true in love, but truly write,
And then believe me, my love is as fair
As any mother's child, though not so bright
As those gold candles fix'd in heaven's air:
Let them say more than like of hearsay well;
I will not praise that purpose not to sell.
My glass shall not persuade me I am old,
So long as youth and thou are of one date;
But when in thee time's furrows I behold,
Then look I death my days should expiate.
For all that beauty that doth cover thee
Is but the seemly raiment of my heart,
Which in thy breast doth live, as thine in me:
How can I then be elder than thou art?
O, therefore, love, be of thyself so wary
As I, not for myself, but for thee will;
Bearing thy heart, which I will keep so chary
As tender nurse her babe from faring ill.
Presume not on thy heart when mine is slain;
Thou gavest me thine, not to give back again.
As an unperfect actor on the stage
Who with his fear is put besides his part,
Or some fierce thing replete with too much rage,
Whose strength's abundance weakens his own heart.
So I, for fear of trust, forget to say
The perfect ceremony of love's rite,
And in mine own love's strength seem to decay,
O'ercharged with burden of mine own love's might.
O, let my books be then the eloquence
And dumb presagers of my speaking breast,
Who plead for love and look for recompense
More than that tongue that more hath more express'd.
O, learn to read what silent love hath writ:
To hear with eyes belongs to love's fine wit.
Mine eye hath play'd the painter and hath stell'd
Thy beauty's form in table of my heart;
My body is the frame wherein 'tis held,
And perspective it is the painter's art.
For through the painter must you see his skill,
To find where your true image pictured lies;
Which in my bosom's shop is hanging still,
That hath his windows glazed with thine eyes.
Now see what good turns eyes for eyes have done:
Mine eyes have drawn thy shape, and thine for me
Are windows to my breast, where-through the sun
Delights to peep, to gaze therein on thee;
Yet eyes this cunning want to grace their art;
They draw but what they see, know not the heart.
Let those who are in favour with their stars
Of public honour and proud titles boast,
Whilst I, whom fortune of such triumph bars,
Unlook'd for joy in that I honour most.
Great princes' favourites their fair leaves spread
But as the marigold at the sun's eye,
And in themselves their pride lies buried,
For at a frown they in their glory die.
The painful warrior famoused for fight,
After a thousand victories once foil'd,
Is from the book of honour razed quite,
And all the rest forgot for which he toil'd:
Then happy I, that love and am beloved
Where I may not remove nor be removed.
Lord of my love, to whom in vassalage
Thy merit hath my duty strongly knit,
To thee I send this written embassage,
To witness duty, not to show my wit:
Duty so great, which wit so poor as mine
May make seem bare, in wanting words to show it,
But that I hope some good conceit of thine
In thy soul's thought, all naked, will bestow it;
Till whatsoever star that guides my moving
Points on me graciously with fair aspect
And puts apparel on my tatter'd loving,
To show me worthy of thy sweet respect:
Then may I dare to boast how I do love thee;
Till then not show my head where thou mayst prove me.
Weary with toil, I haste me to my bed,
The dear repose for limbs with travel tired;
But then begins a journey in my head,
To work my mind, when body's work's expired:
For then my thoughts, from far where I abide,
Intend a zealous pilgrimage to thee,
And keep my drooping eyelids open wide,
Looking on darkness which the blind do see
Save that my soul's imaginary sight
Presents thy shadow to my sightless view,
Which, like a jewel hung in ghastly night,
Makes black night beauteous and her old face new.
Lo! thus, by day my limbs, by night my mind,
For thee and for myself no quiet find.
How can I then return in happy plight,
That am debarr'd the benefit of rest?
When day's oppression is not eased by night,
But day by night, and night by day, oppress'd?
And each, though enemies to either's reign,
Do in consent shake hands to torture me;
The one by toil, the other to complain
How far I toil, still farther off from thee.
I tell the day, to please them thou art bright
And dost him grace when clouds do blot the heaven:
So flatter I the swart-complexion'd night,
When sparkling stars twire not thou gild'st the even.
But day doth daily draw my sorrows longer
And night doth nightly make grief's strength seem stronger.
When, in disgrace with fortune and men's eyes,
I all alone beweep my outcast state
And trouble deal heaven with my bootless cries
And look upon myself and curse my fate,
Wishing me like to one more rich in hope,
Featured like him, like him with friends possess'd,
Desiring this man's art and that man's scope,
With what I most enjoy contented least;
Yet in these thoughts myself almost despising,
Haply I think on thee, and then my state,
Like to the lark at break of day arising
From sullen earth, sings hymns at heaven's gate;
For thy sweet love remember'd such wealth brings
That then I scorn to change my state with kings.
When to the sessions of sweet silent thought
I summon up remembrance of things past,
I sigh the lack of many a thing I sought,
And with old woes new wail my dear time's waste:
Then can I drown an eye, unused to flow,
For precious friends hid in death's dateless night,
And weep afresh love's long since cancell'd woe,
And moan the expense of many a vanish'd sight:
Then can I grieve at grievances foregone,
And heavily from woe to woe tell o'er
The sad account of fore-bemoaned moan,
Which I new pay as if not paid before.
But if the while I think on thee, dear friend,
All losses are restored and sorrows end.
Thy bosom is endeared with all hearts,
Which I by lacking have supposed dead,
And there reigns love and all love's loving parts,
And all those friends which I thought buried.
How many a holy and obsequious tear
Hath dear religious love stol'n from mine eye
As interest of the dead, which now appear
But things removed that hidden in thee lie!
Thou art the grave where buried love doth live,
Hung with the trophies of my lovers gone,
Who all their parts of me to thee did give;
That due of many now is thine alone:
Their images I loved I view in thee,
And thou, all they, hast all the all of me.
If thou survive my well-contented day,
When that churl Death my bones with dust shall cover,
And shalt by fortune once more re-survey
These poor rude lines of thy deceased lover,
Compare them with the bettering of the time,
And though they be outstripp'd by every pen,
Reserve them for my love, not for their rhyme,
Exceeded by the height of happier men.
O, then vouchsafe me but this loving thought:
'Had my friend's Muse grown with this growing age,
A dearer birth than this his love had brought,
To march in ranks of better equipage:
But since he died and poets better prove,
Theirs for their style I'll read, his for his love.'
Full many a glorious morning have I seen
Flatter the mountain-tops with sovereign eye,
Kissing with golden face the meadows green,
Gilding pale streams with heavenly alchemy;
Anon permit the basest clouds to ride
With ugly rack on his celestial face,
And from the forlorn world his visage hide,
Stealing unseen to west with this disgrace:
Even so my sun one early morn did shine
With all triumphant splendor on my brow;
But out, alack! he was but one hour mine;
The region cloud hath mask'd him from me now.
Yet him for this my love no whit disdaineth;
Suns of the world may stain when heaven's sun staineth.
Why didst thou promise such a beauteous day,
And make me travel forth without my cloak,
To let base clouds o'ertake me in my way,
Hiding thy bravery in their rotten smoke?
'Tis not enough that through the cloud thou break,
To dry the rain on my storm-beaten face,
For no man well of such a salve can speak
That heals the wound and cures not the disgrace:
Nor can thy shame give physic to my grief;
Though thou repent, yet I have still the loss:
The offender's sorrow lends but weak relief
To him that bears the strong offence's cross.
Ah! but those tears are pearl which thy love sheds,
And they are rich and ransom all ill deeds.
No more be grieved at that which thou hast done:
Roses have thorns, and silver fountains mud;
Clouds and eclipses stain both moon and sun,
And loathsome canker lives in sweetest bud.
All men make faults, and even I in this,
Authorizing thy trespass with compare,
Myself corrupting, salving thy amiss,
Excusing thy sins more than thy sins are;
For to thy sensual fault I bring in sense--
Thy adverse party is thy advocate--
And 'gainst myself a lawful plea commence:
Such civil war is in my love and hate
That I an accessary needs must be
To that sweet thief which sourly robs from me.
Let me confess that we two must be twain,
Although our undivided loves are one:
So shall those blots that do with me remain
Without thy help by me be borne alone.
In our two loves there is but one respect,
Though in our lives a separable spite,
Which though it alter not love's sole effect,
Yet doth it steal sweet hours from love's delight.
I may not evermore acknowledge thee,
Lest my bewailed guilt should do thee shame,
Nor thou with public kindness honour me,
Unless thou take that honour from thy name:
But do not so; I love thee in such sort
As, thou being mine, mine is thy good report.
As a decrepit father takes delight
To see his active child do deeds of youth,
So I, made lame by fortune's dearest spite,
Take all my comfort of thy worth and truth.
For whether beauty, birth, or wealth, or wit,
Or any of these all, or all, or more,
Entitled in thy parts do crowned sit,
I make my love engrafted to this store:
So then I am not lame, poor, nor despised,
Whilst that this shadow doth such substance give
That I in thy abundance am sufficed
And by a part of all thy glory live.
Look, what is best, that best I wish in thee:
This wish I have; then ten times happy me!
\ No newline at end of file
examples/api_client.py 0 → 100644
View file @ 62f68735
"""Example Python client for vllm.entrypoints.api_server"""
import argparse
import json
from typing import Iterable, List
import requests
def clear_line(n: int = 1) -> None:
LINE_UP = '\033[1A'
LINE_CLEAR = '\x1b[2K'
for _ in range(n):
print(LINE_UP, end=LINE_CLEAR, flush=True)
def post_http_request(prompt: str,
api_url: str,
n: int = 1,
stream: bool = False) -> requests.Response:
headers = {"User-Agent": "Test Client"}
pload = {
"prompt": prompt,
"n": n,
"use_beam_search": True,
"temperature": 0.0,
"max_tokens": 16,
"stream": stream,
}
response = requests.post(api_url, headers=headers, json=pload, stream=True)
return response
def get_streaming_response(response: requests.Response) -> Iterable[List[str]]:
for chunk in response.iter_lines(chunk_size=8192,
decode_unicode=False,
delimiter=b"\0"):
if chunk:
data = json.loads(chunk.decode("utf-8"))
output = data["text"]
yield output
def get_response(response: requests.Response) -> List[str]:
data = json.loads(response.content)
output = data["text"]
return output
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default="localhost")
parser.add_argument("--port", type=int, default=8000)
parser.add_argument("--n", type=int, default=4)
parser.add_argument("--prompt", type=str, default="San Francisco is a")
parser.add_argument("--stream", action="store_true")
args = parser.parse_args()
prompt = args.prompt
api_url = f"http://{args.host}:{args.port}/generate"
n = args.n
stream = args.stream
print(f"Prompt: {prompt!r}\n", flush=True)
response = post_http_request(prompt, api_url, n, stream)
if stream:
num_printed_lines = 0
for h in get_streaming_response(response):
clear_line(num_printed_lines)
num_printed_lines = 0
for i, line in enumerate(h):
num_printed_lines += 1
print(f"Beam candidate {i}: {line!r}", flush=True)
else:
output = get_response(response)
for i, line in enumerate(output):
print(f"Beam candidate {i}: {line!r}", flush=True)
examples/aqlm_example.py 0 → 100644
View file @ 62f68735
import argparse
from vllm import LLM, SamplingParams
def main():
parser = argparse.ArgumentParser(description='AQLM examples')
parser.add_argument('--model',
'-m',
type=str,
default=None,
help='model path, as for HF')
parser.add_argument('--choice',
'-c',
type=int,
default=0,
help='known good models by index, [0-4]')
parser.add_argument('--tensor_parallel_size',
'-t',
type=int,
default=1,
help='tensor parallel size')
args = parser.parse_args()
models = [
"ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf",
"ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf",
"ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf",
"ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf",
"BlackSamorez/TinyLlama-1_1B-Chat-v1_0-AQLM-2Bit-1x16-hf",
]
model = LLM(args.model if args.model is not None else models[args.choice],
tensor_parallel_size=args.tensor_parallel_size)
sampling_params = SamplingParams(max_tokens=100, temperature=0)
outputs = model.generate("Hello my name is",
sampling_params=sampling_params)
print(outputs[0].outputs[0].text)
if __name__ == '__main__':
main()
examples/fp8/README.md 0 → 100644
View file @ 62f68735
# FP8 KV Cache
This utility extracts the KV cache scaling factors from a quantized HF (Hugging Face) model. The extracted scaling factors are saved to a JSON file, which can later be used by vLLM (variable-length language model) during runtime. This tool is particularly useful when the KV cache data type is FP8 and is intended for use on ROCm (AMD GPU) platforms.
## Prerequisites
- Python 3.x
- PyTorch
- NumPy
- Hugging Face Transformers
- Hugging Face Hub
- AMMO
Before incorporating the FP8 datatype for inference workloads, you must adhere to the following steps:
1. Install all necessary prerequisites and dependencies.
2. Convert HF model into a quantized HF model.
3. Extract KV Cache Scaling Factors from quantized HF model.
4. Load KV Cache Scaling Factors into VLLM.
### 2. Convert HF model into a quantized HF model.
Note: The following steps are adapted from the [TensorRT-LLM repository](https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/quantization/README.md).
`quantize.py` (examples/fp8/quantizer/quantize.py) uses the quantization toolkit (AMMO) to calibrate the PyTorch models and export TensorRT-LLM checkpoints. Each TensorRT-LLM checkpoint contains a config file (in .json format) and one or several rank weight files (in .safetensors format).
The detailed quantization toolkit (AMMO) conversion guide for FP8 can be found at `examples/fp8/quantizer/README.md`.
### 3. Extract KV Cache Scaling Factors from quantized HF model.
`extract_scales.py` (examples/fp8/extract_scales.py) can be utilized to extract the KV cache scaling factors from your quantized HF model, however at the moment, this tool exclusively supports Llama 2 models. It is also important to note the following:
1. **File Structure**: The utility operates under the assumption that all parameters, including KV cache scaling factors, corresponding to a particular Tensor Parallelism (TP) rank are stored in a single file. These files must adhere to a specific naming convention where the TP rank is immediately identified after a specific keyword (e.g., "rank") in the filename.
2. **TP Decomposition**: The utility assumes consistency between the TP decomposition employed by the quantizer tool and that used by vLLM.
3. **AMMO Compatibility**: Currently, the generated KV cache scaling factors for AMMO remain uniform across all TP ranks.
```python
# prerequisites:
# - Quantized HF LLaMa 2 model
python3 examples/fp8/extract_scales.py --help
Usage: extract_scales.py [-h] --quantized_model QUANTIZED_MODEL [--load_format {auto,safetensors,npz,pt}] [--output_dir OUTPUT_DIR] [--output_name OUTPUT_NAME] [--tp_size TP_SIZE]
KV Scale Extraction Example
optional arguments:
--quantized_model: Specify either the local path to, or name of, a quantized HF model. It is expected that the quantization format is FP8_E4M3, for use on ROCm (AMD GPU).
Optional arguments:
--cache_dir: Specify a cache directory to use in the event of a HF model download. (Default: None)
--load_format: Specify the format of the model's tensor files containing the KV cache scaling factors. (Choices: auto, safetensors, npz, pt; Default: auto)
--revision: Specify the model's revision number. (Default: None)
--output_dir: Specify the output directory. By default the KV cache scaling factors will be saved in the model directory. (Default: None)
--output_name: Specify the output filename. (Default: kv_cache_scales.json)
--tp_size: Specify the tensor-parallel (TP) size that the quantized model should correspond to. If specified, during KV cache scaling factor extraction the observed TP size will be checked against this and an error will be raised if there is a mismatch. (Default: None)
```
```python
Example:
python3 examples/fp8/extract_scales.py --quantized_model <QUANTIZED_MODEL_DIR> --tp_size <TENSOR_PARALLEL_SIZE> --output_dir <PATH_TO_OUTPUT_DIR>
```
### 4. Load KV Cache Scaling Factors into VLLM.
This script evaluates the inference throughput of language models using various backends such as vLLM. It measures the time taken to process a given number of prompts and generate sequences for each prompt. The recently generated KV cache scaling factors are now integrated into the benchmarking process and allow for KV cache scaling factors to be utilized for FP8.
```python
# prerequisites:
# - LLaMa 2 kv_cache_scales.json file
python3 benchmarks/benchmark_throughput.py --help
usage: benchmark_throughput.py [-h] [--backend {vllm,hf,mii}] [--dataset DATASET] [--input-len INPUT_LEN] [--output-len OUTPUT_LEN] [--model MODEL]
[--tokenizer TOKENIZER] [--quantization {awq,gptq,squeezellm,None}] [--tensor-parallel-size TENSOR_PARALLEL_SIZE] [--n N]
[--use-beam-search] [--num-prompts NUM_PROMPTS] [--seed SEED] [--hf-max-batch-size HF_MAX_BATCH_SIZE] [--trust-remote-code]
[--max-model-len MAX_MODEL_LEN] [--dtype {auto,half,float16,bfloat16,float,float32}] [--enforce-eager] [--kv-cache-dtype {auto,fp8}]
[--quantization-param-path KV_CACHE_quantization_param_path]
Benchmark Throughput Example
optional arguments:
-h, --help show this help message and exit
--backend {vllm,hf,mii}
--dataset DATASET Path to the dataset.
--input-len INPUT_LEN Input prompt length for each request
--output-len OUTPUT_LEN Output length for each request. Overrides the output length from the dataset.
--model MODEL
--tokenizer TOKENIZER
--quantization {awq,gptq,squeezellm,None}, -q {awq,gptq,squeezellm,None}
--tensor-parallel-size TENSOR_PARALLEL_SIZE, -tp TENSOR_PARALLEL_SIZE
--n N Number of generated sequences per prompt.
--use-beam-search
--num-prompts NUM_PROMPTS Number of prompts to process.
--seed SEED
--hf-max-batch-size HF_MAX_BATCH_SIZE Maximum batch size for HF backend.
--trust-remote-code trust remote code from huggingface
--max-model-len MAX_MODEL_LEN Maximum length of a sequence (including prompt and output). If None, will be derived from the model.
--dtype {auto,half,float16,bfloat16,float,float32} data type for model weights and activations. The "auto" option will use FP16 precision for FP32 and FP16 models, and BF16 precision for BF16 models.
--enforce-eager enforce eager execution
--kv-cache-dtype {auto,fp8} Data type for kv cache storage. If "auto", will use model data type. FP8_E5M2 (without scaling) is only supported on cuda version greater than 11.8. On ROCm (AMD GPU), FP8_E4M3 is instead supported ```for common inference criteria.
--quantization-param-path QUANT_PARAM_JSON Path to the JSON file containing the KV cache scaling factors. This should generally be supplied, when KV cache dtype is FP8. Otherwise, KV cache scaling factors default to 1.0, which may cause accuracy issues. FP8_E5M2 (without scaling) is only supported on cuda version greater than 11.8. On ROCm (AMD GPU), FP8_E4M3 is instead supported for common inference criteria.
```
```
Example:
python3 benchmarks/benchmark_throughput.py --input-len <INPUT_LEN> --output-len <OUTPUT_LEN> -tp <TENSOR_PARALLEL_SIZE> --kv-cache-dtype fp8 --quantization-param-path <path/to/kv_cache_scales.json> --model <path-to-llama2>
```python
examples/fp8/extract_scales.py 0 → 100644
View file @ 62f68735
import argparse
import glob
import json
import os
from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple
import numpy as np
import torch
from safetensors.torch import safe_open
from vllm.model_executor.layers.quantization.schema import QuantParamSchema
# Adapted from vllm/model_executor/model_loader/weight_utils.py
# The main differences are that we add the NPZ format and simplify
# its functionality drastically for our purposes (e.g. we assume that
# the quantized model exists locally and there is no need to download it)
def _prepare_hf_weights(
quantized_model_dir: str,
load_format: str = "auto",
fall_back_to_pt: bool = True,
) -> Tuple[str, List[str], bool]:
if not os.path.isdir(quantized_model_dir):
raise FileNotFoundError(
f"The quantized model directory `{quantized_model_dir}` "
"does not exist.")
use_safetensors = False
# Some quantized models use .pt files for storing the weights.
if load_format == "auto":
allow_patterns = ["*.safetensors", "*.bin"]
elif load_format == "safetensors":
use_safetensors = True
allow_patterns = ["*.safetensors"]
elif load_format == "pt":
allow_patterns = ["*.pt"]
elif load_format == "npz":
allow_patterns = ["*.npz"]
else:
raise ValueError(f"Unknown load_format: {load_format}")
if fall_back_to_pt:
allow_patterns += ["*.pt"]
hf_weights_files: List[str] = []
for pattern in allow_patterns:
hf_weights_files += glob.glob(
os.path.join(quantized_model_dir, pattern))
if len(hf_weights_files) > 0:
if pattern == "*.safetensors":
use_safetensors = True
break
if not use_safetensors:
# Exclude files that are not needed for inference.
# https://github.com/huggingface/transformers/blob/v4.34.0/src/transformers/trainer.py#L227-L233
blacklist = [
"training_args.bin",
"optimizer.bin",
"optimizer.pt",
"scheduler.pt",
"scaler.pt",
]
hf_weights_files = [
f for f in hf_weights_files
if not any(f.endswith(x) for x in blacklist)
]
if len(hf_weights_files) == 0:
raise RuntimeError(
f"Cannot find any model weights with `{quantized_model_dir}`")
return hf_weights_files, use_safetensors
# Adapted from vllm/model_executor/model_loader/weight_utils.py
def _hf_tensorfile_iterator(filename: str, load_format: str,
use_safetensors: bool):
if load_format == "npz":
assert not use_safetensors
with np.load(filename) as data:
for name in data.files:
param = torch.from_numpy(data[name])
yield name, param
elif use_safetensors:
with safe_open(filename, framework="pt") as f:
for name in f.keys(): # NOQA: SIM118
param = f.get_tensor(name)
yield name, param
else:
state = torch.load(filename, map_location="cpu")
for name, param in state.items():
yield name, param
del state
torch.cuda.empty_cache()
def _kv_scales_extractor(
hf_tensor_files: Iterable[str],
use_safetensors: bool,
rank_keyword: str = "rank",
expected_tp_size: Optional[int] = None) -> Dict[int, Dict[int, float]]:
"""
Given a list of files containing tensor data, attempt to extract KV cache
scales from these files. Intended as a helper function taking in the output
from _prepare_hf_weights.
Args:
rank_keyword Matches the number immediately after this keyword in the
tensor filename to determine the TP rank corresponding
to said tensor file
expected_tp_size If specified, the TP size of the tensor files is checked
against this and an error is raised if they don't match.
Returns a dictionary mapping TP ranks to their relevant KV cache scales.
The per-rank scales are themselves represented as a dictionary of layer
indices to the respective per-layer scale.
"""
for char in rank_keyword:
assert not char.isdecimal(
), f"Rank keyword {rank_keyword} contains a numeric character!"
rank_scales_map = {}
for tensor_file in hf_tensor_files:
try:
rank_idx = tensor_file.find(rank_keyword)
if rank_idx != -1:
start_idx = rank_idx + len(rank_keyword)
stop_idx = start_idx
while stop_idx < len(
tensor_file) and tensor_file[stop_idx].isdecimal():
stop_idx += 1
if stop_idx == start_idx:
raise RuntimeError("Did not find rank # in filename.")
rank = int(tensor_file[start_idx:stop_idx])
elif len(hf_tensor_files) == 1:
# Since there is only one tensor file, we can assume
# that it's intended for TP rank 0
rank = 0
else:
raise RuntimeError(
f"Filename does not contain '{rank_keyword}'.")
except RuntimeError:
print("Unable to determine TP rank "
f"corresponding to file '{tensor_file}'")
raise
if rank not in rank_scales_map:
layer_scales_map = {}
rank_scales_map[rank] = layer_scales_map
else:
raise RuntimeError(
f"Tensor file '{tensor_file}' shares TP rank {rank} "
"with another tensor file.")
module_delimiter = ":" if args.load_format == "npz" else "."
for name, param in _hf_tensorfile_iterator(tensor_file,
args.load_format,
use_safetensors):
if "kv_cache_scaling_factor" in name:
nums = [
int(s) for s in name.split(module_delimiter)
if s.isdecimal()
]
assert len(
nums) == 1, f"Could not determine layer idx for {name}"
layer_idx = nums[0]
assert layer_idx not in layer_scales_map, f"Duplicate scaling"\
f" factor corresponding to layer {layer_idx}"
try:
layer_scales_map[layer_idx] = param.item()
except RuntimeError:
print(
"This utility supports only per-tensor scalar scales "
f"for now. The tensor\n {name} = {param} \nis an "
"invalid scale factor.")
raise
if all(
len(layer_scales_map) == 0
for layer_scales_map in rank_scales_map.values()):
# Note: this is true even if the rank_scales_map is empty
print("WARNING: No KV cache scale factors found. No output saved.")
return None
empirical_tp_world_size = max(rank_scales_map.keys()) + 1
if expected_tp_size is not None:
assert expected_tp_size == empirical_tp_world_size, \
f"User expected TP world size = {expected_tp_size} " \
"from model but tool is expecting TP world size = " \
f"{empirical_tp_world_size} from model instead."
for i in range(empirical_tp_world_size):
assert i in rank_scales_map, "Expected TP world size = "\
f"{empirical_tp_world_size} but did not find KV " \
f"cache scaling factors for TP rank {i}"
print(f"Found TP world size = {empirical_tp_world_size} "
"when extracting KV cache scales!")
return rank_scales_map
def _metadata_extractor(quantized_model_dir: str,
metadata_extract_fns: \
Dict[str, Callable[[Dict[str, Any]], Any]]) \
-> Dict[str, Any]:
"""
Given a directory containing quantized model files, this function
aims to extract metadata from the JSON files within this directory.
Each JSON file is expected to represent a dictionary in JSON
format (referred to as a "JSON-dictionary"). Metadata extraction is
defined by a dictionary called metadata_extract_fns, where each
metadata field name is mapped to an extraction function.
These extraction functions are designed to take a JSON-dictionary
as their only argument and return the corresponding metadata.
While extraction functions are permitted to raise exceptions, they
should only raise a KeyError or ValueError if the metadata field
cannot be extracted from the current JSON-dictionary, yet there's
a possibility of finding it in another JSON-dictionary.
The function returns a dictionary that maps metadata fields to
their extracted data. The keys of this dictionary correspond exactly
to those in metadata_extract_fns. If any fields fail to be extracted,
their corresponding values are set to None, and a warning is printed.
"""
if not os.path.isdir(quantized_model_dir):
raise FileNotFoundError(
f"The quantized model directory `{quantized_model_dir}` "
"does not exist.")
metadata_files = glob.glob(os.path.join(quantized_model_dir, "*.json"))
result = {}
for file in metadata_files:
with open(file) as f:
try:
metadata = json.load(f)
except json.JSONDecodeError:
print(f"Could not parse `{file}` as a valid metadata file,"
" skipping it.")
continue
if not isinstance(metadata, dict):
print(f"The file `{file}` does not correspond to a "
"JSON-serialized dictionary, skipping it.")
continue
for metadata_name, extract_fn in metadata_extract_fns.items():
try:
metadata_info = extract_fn(metadata)
if metadata_name not in result:
result[metadata_name] = metadata_info
elif metadata_info != result[metadata_name]:
raise RuntimeError(
"Metadata mismatch! Originally found "
f"{metadata_name} = {result[metadata_name]} but "
f"now found {metadata_name} = {metadata_info} in "
f"`{file}`")
except KeyError:
# It is possible that a given file does not contain some
# of our selected metadata as it could be located in some
# other metadata file.
# 'EFINAE': extract_fn failure is not an error.
pass
except ValueError:
# See above.
pass
# Warn if we cannot find any of the requested metadata
for metadata_name in metadata_extract_fns:
if metadata_name not in result:
print("WARNING: Unable to find requested metadata field "
f"`{metadata_name}`, setting it to None.")
result[metadata_name] = None
return result
def main(args):
metadata_extract_fns = {
"model_type": lambda json_dict: json_dict["layers"][0]["decoder_type"],
"tp_size": lambda json_dict: int(json_dict["tensor_parallel"]),
"model_dtype": lambda json_dict: json_dict["dtype"]
}
recovered_metadata = _metadata_extractor(args.quantized_model,
metadata_extract_fns)
if args.tp_size is not None:
metadata_tp_size = recovered_metadata["tp_size"]
if metadata_tp_size is not None:
assert args.tp_size == metadata_tp_size, \
f"User expected TP world size = {args.tp_size} " \
f"but found TP world size = {metadata_tp_size} from metadata!"
expected_tp_size = args.tp_size or recovered_metadata["tp_size"]
rank_keyword = "rank"
hf_tensor_files, use_safetensors = _prepare_hf_weights(
args.quantized_model, args.load_format)
rank_scales_map = _kv_scales_extractor(hf_tensor_files, use_safetensors,
rank_keyword, expected_tp_size)
# Postprocess: formatting to the current schema. Consider pulling it
# out into a dedicated function should it ever become more complicated.
rank_scales_map = {
rank: {k: scale[k]
for k in sorted(scale.keys())}
for rank, scale in rank_scales_map.items()
}
# TODO: Expand this with activation and weights scaling factors when
# they are used in the future
schema = QuantParamSchema(
model_type=recovered_metadata["model_type"],
kv_cache={
"dtype": ("float8_e4m3fn" if len(rank_scales_map) > 0 else
recovered_metadata["model_dtype"]),
"scaling_factor":
rank_scales_map
},
)
if args.output_dir is None:
output_file = os.path.join(args.quantized_model, args.output_name)
else:
if not os.path.isdir(args.output_dir):
os.makedirs(args.output_dir, exist_ok=True)
output_file = os.path.join(args.output_dir, args.output_name)
with open(output_file, 'w') as f:
f.write(schema.model_dump_json(indent=4))
print(f"Completed! KV cache scaling factors saved to {output_file}")
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="This simple utility extracts the "
"KV cache scaling factors from a quantized HF model "
"and saves them to a JSON file compatible with later "
"use by vLLM (pass this file to the appropriate "
"runtime typically using the argument "
"--quantization-param-path <filename>). This is only used "
"if the KV cache dtype is FP8 and on ROCm (AMD GPU).")
parser.add_argument(
"--quantized_model",
help="Specify the directory containing a single quantized HF model. "
"It is expected that the quantization format is FP8_E4M3, for use "
"on ROCm (AMD GPU).",
required=True)
parser.add_argument(
"--load_format",
help="Optionally specify the format of the model's tensor files "
"containing the KV cache scaling factors.",
choices=["auto", "safetensors", "npz", "pt"],
default="auto")
parser.add_argument(
"--output_dir",
help="Optionally specify the output directory. By default the "
"KV cache scaling factors will be saved in the model directory, "
"however you can override this behavior here.",
default=None)
parser.add_argument(
"--output_name",
help="Optionally specify the output filename.",
# TODO: Change this once additional scaling factors are enabled
default="kv_cache_scales.json")
parser.add_argument(
"--tp_size",
help="Optionally specify the tensor-parallel (TP) size that the "
"quantized model should correspond to. If specified, during KV "
"cache scaling factor extraction the observed TP size will be "
"checked against this and an error will be raised if there is "
"a mismatch. If not specified, the quantized model's expected "
"TP size is instead inferred from the largest TP rank observed. "
"The expected TP size is cross-checked against the TP ranks "
"observed in the quantized model and an error is raised if any "
"discrepancies are found.",
default=None,
type=int)
args = parser.parse_args()
main(args)
examples/fp8/quantizer/README.md 0 → 100644
View file @ 62f68735
### Quantizer Utilities
`quantize.py`: NVIDIA Quantization utilities using AMMO, ported from TensorRT-LLM:
`https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/quantization/quantize.py`
### Prerequisite
#### AMMO (AlgorithMic Model Optimization) Installation: nvidia-ammo 0.7.1 or later
`pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com nvidia-ammo`
#### AMMO Download (code and docs)
`https://developer.nvidia.com/downloads/assets/cuda/files/nvidia-ammo/nvidia_ammo-0.5.0.tar.gz`
`https://developer.nvidia.com/downloads/assets/cuda/files/nvidia-ammo/nvidia_ammo-0.7.1.tar.gz`
### Usage
#### Run on H100 system for speed if FP8; number of GPUs depends on the model size
#### Example: quantize Llama2-7b model from HF to FP8 with FP8 KV Cache:
`python quantize.py --model_dir ./ll2-7b --dtype float16 --qformat fp8 --kv_cache_dtype fp8 --output_dir ./ll2_7b_fp8 --calib_size 512 --tp_size 1`
Outputs: model structure, quantized model & parameters (with scaling factors) are in JSON and Safetensors (npz is generated only for the reference)
```
# ll ./ll2_7b_fp8/
total 19998244
drwxr-xr-x 2 root root 4096 Feb 7 01:08 ./
drwxrwxr-x 8 1060 1061 4096 Feb 7 01:08 ../
-rw-r--r-- 1 root root 176411 Feb 7 01:08 llama_tp1.json
-rw-r--r-- 1 root root 13477087480 Feb 7 01:09 llama_tp1_rank0.npz
-rw-r--r-- 1 root root 7000893272 Feb 7 01:08 rank0.safetensors
#
```
examples/fp8/quantizer/quantize.py 0 → 100644
View file @ 62f68735
# SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved. # noqa: E501
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Adapted from examples/quantization/hf_ptq.py
"""
import argparse
import copy
import json
import random
import time
import ammo.torch.quantization as atq
import numpy as np
import torch
from ammo.torch.export import export_model_config
from datasets import load_dataset
from torch.utils.data import DataLoader
from transformers import AutoModelForCausalLM, AutoTokenizer
RAND_SEED = 1234
MAX_SEQ_LEN = 2048
EMPTY_CFG = {
"quant_cfg": {
"*weight_quantizer": {
"enable": False,
},
"*input_quantizer": {
"enable": False
},
"*lm_head*": {
"enable": False
},
"*output_layer*": {
"enable": False
},
"default": {
"enable": False
},
},
"algorithm": "max",
}
KV_CACHE_CFG = {
"*.query_key_value.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
"*.Wqkv.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
"*.W_pack.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
"*.c_attn.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
"*.k_proj.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
"*.v_proj.output_quantizer": {
"num_bits": 8,
"axis": None,
"enable": True
},
}
QUANT_CFG_CHOICES = {
"int8_sq": atq.INT8_SMOOTHQUANT_CFG,
"fp8": atq.FP8_DEFAULT_CFG,
"int4_awq": atq.INT4_AWQ_CFG,
"w4a8_awq": atq.W4A8_AWQ_BETA_CFG,
"int8_wo": EMPTY_CFG,
"int4_wo": EMPTY_CFG,
"full_prec": EMPTY_CFG,
}
MODEL_NAME_PATTERN_MAP = {
"GPT2": "gpt2",
"Xverse": "llama",
"Llama": "llama",
"Mistral": "llama",
"GPTJ": "gptj",
"FalconForCausalLM": "falcon",
"RWForCausalLM": "falcon",
"baichuan": "baichuan",
"MPT": "mpt",
"Bloom": "bloom",
"ChatGLM": "chatglm",
"QWen": "qwen",
}
def get_tokenizer(ckpt_path, max_seq_len=MAX_SEQ_LEN, model_type=None):
print(f"Initializing tokenizer from {ckpt_path}")
tokenizer = AutoTokenizer.from_pretrained(
ckpt_path,
model_max_length=max_seq_len,
padding_side="left",
trust_remote_code=True,
)
if model_type and model_type == "qwen":
# qwen use token id 151643 as pad and eos tokens
tokenizer.pad_token = tokenizer.convert_ids_to_tokens(151643)
tokenizer.eos_token = tokenizer.convert_ids_to_tokens(151643)
# can't set attribute 'pad_token' for "<unk>"
if tokenizer.pad_token != "<unk>":
tokenizer.pad_token = tokenizer.eos_token
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
assert (tokenizer.pad_token
is not None), f"Pad token for {model_type} cannot be set!"
return tokenizer
def get_model(ckpt_path, dtype="fp16", device="cuda"):
print(f"Initializing model from {ckpt_path}")
if dtype == "bf16" or dtype == "bfloat16":
dtype = torch.bfloat16
elif dtype == "fp16" or dtype == "float16":
dtype = torch.float16
elif dtype == "fp32" or dtype == "float32":
dtype = torch.float32
else:
raise NotImplementedError(f"Unknown dtype {dtype}")
# model_kwargs = {"torch_dtype": dtype}
model_kwargs = {"torch_dtype": "auto"}
model = AutoModelForCausalLM.from_pretrained(ckpt_path,
device_map="auto",
**model_kwargs,
trust_remote_code=True)
model.eval()
model_dtype = next(model.parameters()).dtype
if dtype != model_dtype:
print("[TensorRT-LLM][WARNING] The manually set model data type is "
f"{dtype}, but the data type of the HuggingFace model is "
f"{model_dtype}.")
return model
def get_model_type(model):
for k, v in MODEL_NAME_PATTERN_MAP.items():
if k.lower() in type(model).__name__.lower():
return v
return None
def get_calib_dataloader(data="cnn_dailymail",
tokenizer=None,
batch_size=1,
calib_size=512,
block_size=512,
device=None):
print("Loading calibration dataset")
if data == "pileval":
dataset = load_dataset(
"json",
data_files="https://the-eye.eu/public/AI/pile/val.jsonl.zst",
split="train")
dataset = dataset["text"][:calib_size]
elif data == "cnn_dailymail":
dataset = load_dataset("cnn_dailymail", name="3.0.0", split="train")
dataset = dataset["article"][:calib_size]
else:
raise NotImplementedError
batch_encoded = tokenizer.batch_encode_plus(dataset,
return_tensors="pt",
padding="max_length",
truncation=True,
max_length=block_size)
if device:
batch_encoded = batch_encoded.to(device)
batch_encoded = batch_encoded["input_ids"]
calib_dataloader = DataLoader(batch_encoded,
batch_size=batch_size,
shuffle=False)
return calib_dataloader
def quantize_model(model, quant_cfg, calib_dataloader=None):
def calibrate_loop():
if calib_dataloader is None:
return
"""Adjusts weights and scaling factors based on selected algorithms."""
for idx, data in enumerate(calib_dataloader):
print(f"Calibrating batch {idx}")
model(data)
print("Starting quantization...")
start_time = time.time()
atq.quantize(model, quant_cfg, forward_loop=calibrate_loop)
end_time = time.time()
print("Quantization done. Total time used: {:.2f} s.".format(end_time -
start_time))
return model
def main(args):
if not torch.cuda.is_available():
raise EnvironmentError("GPU is required for inference.")
random.seed(RAND_SEED)
np.random.seed(RAND_SEED)
model = get_model(args.model_dir, args.dtype, args.device)
model_type = get_model_type(model)
tokenizer = get_tokenizer(args.model_dir, model_type=model_type)
if args.qformat in ["full_prec", "int8_wo", "int4_wo"
] and args.kv_cache_dtype is None:
print(f"No quantization applied, export {args.dtype} model")
else:
if "awq" in args.qformat:
if args.calib_size > 32:
print("AWQ calibration could take longer with calib_size = "
f"{args.calib_size}, Using calib_size=32 instead")
args.calib_size = 32
print("\nAWQ calibration could take longer than other calibration "
"methods. Please increase the batch size to speed up the "
"calibration process. Batch size can be set by adding the "
"argument --batch_size <batch_size> to the command line.\n")
calib_dataloader = get_calib_dataloader(
tokenizer=tokenizer,
batch_size=args.batch_size,
calib_size=args.calib_size,
device=args.device,
)
if args.qformat in QUANT_CFG_CHOICES:
quant_cfg = QUANT_CFG_CHOICES[args.qformat]
else:
raise ValueError(
f"Unsupported quantization format: {args.qformat}")
if "awq" in args.qformat:
quant_cfg = copy.deepcopy(QUANT_CFG_CHOICES[args.qformat])
weight_quantizer = quant_cfg["quant_cfg"][
"*weight_quantizer"] # type: ignore
if isinstance(weight_quantizer, list):
weight_quantizer = weight_quantizer[0]
weight_quantizer["block_sizes"][-1] = args.awq_block_size
if args.kv_cache_dtype is not None:
if args.kv_cache_dtype == "fp8":
for value in KV_CACHE_CFG.values():
value.update({"num_bits": (4, 3)}) # type: ignore
quant_cfg["quant_cfg"].update(KV_CACHE_CFG) # type: ignore
print(quant_cfg)
model = quantize_model(model, quant_cfg, calib_dataloader)
with torch.inference_mode():
if model_type is None:
print(f"Unknown model type {type(model).__name__}. Continue "
"exporting...")
model_type = f"unknown:{type(model).__name__}"
export_path = args.output_dir
start_time = time.time()
if args.qformat == "int4_awq" and model_type == "qwen":
torch.save(model.state_dict(), export_path)
else:
export_npz = (model_type not in [
'gptj', 'falcon', 'chatglm', 'mpt', 'llama', 'baichuan'
])
# export safetensors
export_model_config(
model,
model_type,
getattr(torch, args.dtype),
export_dir=export_path,
inference_tensor_parallel=args.tp_size,
inference_pipeline_parallel=args.pp_size,
# export_tensorrt_llm_config=(not export_npz),
export_tensorrt_llm_config=False,
export_npz=export_npz)
# Workaround for wo quantization
if args.qformat in ["int8_wo", "int4_wo", "full_prec"]:
with open(f"{export_path}/config.json", 'r') as f:
tensorrt_llm_config = json.load(f)
if args.qformat == "int8_wo":
tensorrt_llm_config["quantization"]["quant_algo"] = 'W8A16'
elif args.qformat == "int4_wo":
tensorrt_llm_config["quantization"]["quant_algo"] = 'W4A16'
else:
tensorrt_llm_config["quantization"]["quant_algo"] = None
with open(f"{export_path}/config.json", "w") as f:
json.dump(tensorrt_llm_config, f, indent=4)
end_time = time.time()
print("Quantized model exported to {} \nTotal time used {:.2f} s.".
format(export_path, end_time - start_time))
if __name__ == "__main__":
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--model_dir",
help="Specify where the HuggingFace model is",
required=True)
parser.add_argument("--device", default="cuda")
parser.add_argument("--dtype", help="Model data type.", default="float16")
parser.add_argument(
"--qformat",
help="Quantization format.",
default="full_prec",
choices=[
"fp8", "int8_sq", "int4_awq", "w4a8_awq", "int8_wo", "int4_wo",
"full_prec"
],
)
parser.add_argument("--batch_size",
help="Batch size for calibration.",
type=int,
default=1)
parser.add_argument("--calib_size",
help="Number of samples for calibration.",
type=int,
default=512)
parser.add_argument("--output_dir", default="exported_model")
parser.add_argument("--tp_size", type=int, default=1)
parser.add_argument("--pp_size", type=int, default=1)
parser.add_argument("--awq_block_size", type=int, default=128)
parser.add_argument("--kv_cache_dtype",
help="KV Cache dtype.",
default=None,
choices=["int8", "fp8", None])
args = parser.parse_args()
main(args)
examples/gradio_openai_chatbot_webserver.py 0 → 100644
View file @ 62f68735
import argparse
import gradio as gr
from openai import OpenAI
# Argument parser setup
parser = argparse.ArgumentParser(
description='Chatbot Interface with Customizable Parameters')
parser.add_argument('--model-url',
type=str,
default='http://localhost:8000/v1',
help='Model URL')
parser.add_argument('-m',
'--model',
type=str,
required=True,
help='Model name for the chatbot')
parser.add_argument('--temp',
type=float,
default=0.8,
help='Temperature for text generation')
parser.add_argument('--stop-token-ids',
type=str,
default='',
help='Comma-separated stop token IDs')
parser.add_argument("--host", type=str, default=None)
parser.add_argument("--port", type=int, default=8001)
# Parse the arguments
args = parser.parse_args()
# Set OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = args.model_url
# Create an OpenAI client to interact with the API server
client = OpenAI(
api_key=openai_api_key,
base_url=openai_api_base,
)
def predict(message, history):
# Convert chat history to OpenAI format
history_openai_format = [{
"role": "system",
"content": "You are a great ai assistant."
}]
for human, assistant in history:
history_openai_format.append({"role": "user", "content": human})
history_openai_format.append({
"role": "assistant",
"content": assistant
})
history_openai_format.append({"role": "user", "content": message})
# Create a chat completion request and send it to the API server
stream = client.chat.completions.create(
model=args.model, # Model name to use
messages=history_openai_format, # Chat history
temperature=args.temp, # Temperature for text generation
stream=True, # Stream response
extra_body={
'repetition_penalty':
1,
'stop_token_ids': [
int(id.strip()) for id in args.stop_token_ids.split(',')
if id.strip()
] if args.stop_token_ids else []
})
# Read and return generated text from response stream
partial_message = ""
for chunk in stream:
partial_message += (chunk.choices[0].delta.content or "")
yield partial_message
# Create and launch a chat interface with Gradio
gr.ChatInterface(predict).queue().launch(server_name=args.host,
server_port=args.port,
share=True)
examples/gradio_webserver.py 0 → 100644
View file @ 62f68735
import argparse
import json
import gradio as gr
import requests
def http_bot(prompt):
headers = {"User-Agent": "vLLM Client"}
pload = {
"prompt": prompt,
"stream": True,
"max_tokens": 128,
}
response = requests.post(args.model_url,
headers=headers,
json=pload,
stream=True)
for chunk in response.iter_lines(chunk_size=8192,
decode_unicode=False,
delimiter=b"\0"):
if chunk:
data = json.loads(chunk.decode("utf-8"))
output = data["text"][0]
yield output
def build_demo():
with gr.Blocks() as demo:
gr.Markdown("# vLLM text completion demo\n")
inputbox = gr.Textbox(label="Input",
placeholder="Enter text and press ENTER")
outputbox = gr.Textbox(label="Output",
placeholder="Generated result from the model")
inputbox.submit(http_bot, [inputbox], [outputbox])
return demo
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--host", type=str, default=None)
parser.add_argument("--port", type=int, default=8001)
parser.add_argument("--model-url",
type=str,
default="http://localhost:8000/generate")
args = parser.parse_args()
demo = build_demo()
demo.queue().launch(server_name=args.host,
server_port=args.port,
share=True)
examples/llava_example.py 0 → 100644
View file @ 62f68735
import argparse
import os
import subprocess
import torch
from PIL import Image
from vllm import LLM
from vllm.multimodal.image import ImageFeatureData, ImagePixelData
# The assets are located at `s3://air-example-data-2/vllm_opensource_llava/`.
# You can use `.buildkite/download-images.sh` to download them
def run_llava_pixel_values(*, disable_image_processor: bool = False):
llm = LLM(
model="llava-hf/llava-1.5-7b-hf",
image_input_type="pixel_values",
image_token_id=32000,
image_input_shape="1,3,336,336",
image_feature_size=576,
disable_image_processor=disable_image_processor,
)
prompt = "<image>" * 576 + (
"\nUSER: What is the content of this image?\nASSISTANT:")
if disable_image_processor:
image = torch.load("images/stop_sign_pixel_values.pt")
else:
image = Image.open("images/stop_sign.jpg")
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": ImagePixelData(image),
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
def run_llava_image_features():
llm = LLM(
model="llava-hf/llava-1.5-7b-hf",
image_input_type="image_features",
image_token_id=32000,
image_input_shape="1,576,1024",
image_feature_size=576,
)
prompt = "<image>" * 576 + (
"\nUSER: What is the content of this image?\nASSISTANT:")
image: torch.Tensor = torch.load("images/stop_sign_image_features.pt")
outputs = llm.generate({
"prompt": prompt,
"multi_modal_data": ImageFeatureData(image),
})
for o in outputs:
generated_text = o.outputs[0].text
print(generated_text)
def main(args):
if args.type == "pixel_values":
run_llava_pixel_values()
else:
run_llava_image_features()
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Demo on Llava")
parser.add_argument("--type",
type=str,
choices=["pixel_values", "image_features"],
default="pixel_values",
help="image input type")
args = parser.parse_args()
# Download from s3
s3_bucket_path = "s3://air-example-data-2/vllm_opensource_llava/"
local_directory = "images"
# Make sure the local directory exists or create it
os.makedirs(local_directory, exist_ok=True)
# Use AWS CLI to sync the directory, assume anonymous access
subprocess.check_call([
"aws",
"s3",
"sync",
s3_bucket_path,
local_directory,
"--no-sign-request",
])
main(args)
examples/llm_engine_example.py 0 → 100644
View file @ 62f68735
import argparse
from typing import List, Tuple
from vllm import EngineArgs, LLMEngine, RequestOutput, SamplingParams
def create_test_prompts() -> List[Tuple[str, SamplingParams]]:
"""Create a list of test prompts with their sampling parameters."""
return [
("A robot may not injure a human being",
SamplingParams(temperature=0.0, logprobs=1, prompt_logprobs=1)),
("To be or not to be,",
SamplingParams(temperature=0.8, top_k=5, presence_penalty=0.2)),
("What is the meaning of life?",
SamplingParams(n=2,
best_of=5,
temperature=0.8,
top_p=0.95,
frequency_penalty=0.1)),
("It is only with the heart that one can see rightly",
SamplingParams(n=3, best_of=3, use_beam_search=True,
temperature=0.0)),
]
def process_requests(engine: LLMEngine,
test_prompts: List[Tuple[str, SamplingParams]]):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
while test_prompts or engine.has_unfinished_requests():
if test_prompts:
prompt, sampling_params = test_prompts.pop(0)
engine.add_request(str(request_id), prompt, sampling_params)
request_id += 1
request_outputs: List[RequestOutput] = engine.step()
for request_output in request_outputs:
if request_output.finished:
print(request_output)
def initialize_engine(args: argparse.Namespace) -> LLMEngine:
"""Initialize the LLMEngine from the command line arguments."""
engine_args = EngineArgs.from_cli_args(args)
return LLMEngine.from_engine_args(engine_args)
def main(args: argparse.Namespace):
"""Main function that sets up and runs the prompt processing."""
engine = initialize_engine(args)
test_prompts = create_test_prompts()
process_requests(engine, test_prompts)
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Demo on using the LLMEngine class directly')
parser = EngineArgs.add_cli_args(parser)
args = parser.parse_args()
main(args)
examples/logging_configuration.md 0 → 100644
View file @ 62f68735
# Logging Configuration
vLLM leverages Python's `logging.config.dictConfig` functionality to enable
robust and flexible configuration of the various loggers used by vLLM.
vLLM offers two environment variables that can be used to accommodate a range
of logging configurations that range from simple-and-inflexible to
more-complex-and-more-flexible.
- No vLLM logging (simple and inflexible)
- Set `VLLM_CONFIGURE_LOGGING=0` (leaving `VLLM_LOGGING_CONFIG_PATH` unset)
- vLLM's default logging configuration (simple and inflexible)
- Leave `VLLM_CONFIGURE_LOGGING` unset or set `VLLM_CONFIGURE_LOGGING=1`
- Fine-grained custom logging configuration (more complex, more flexible)
- Leave `VLLM_CONFIGURE_LOGGING` unset or set `VLLM_CONFIGURE_LOGGING=1` and
set `VLLM_LOGGING_CONFIG_PATH=<path-to-logging-config.json>`
## Logging Configuration Environment Variables
### `VLLM_CONFIGURE_LOGGING`
`VLLM_CONFIGURE_LOGGING` controls whether or not vLLM takes any action to
configure the loggers used by vLLM. This functionality is enabled by default,
but can be disabled by setting `VLLM_CONFIGURE_LOGGING=0` when running vLLM.
If `VLLM_CONFIGURE_LOGGING` is enabled and no value is given for
`VLLM_LOGGING_CONFIG_PATH`, vLLM will use built-in default configuration to
configure the root vLLM logger. By default, no other vLLM loggers are
configured and, as such, all vLLM loggers defer to the root vLLM logger to make
all logging decisions.
If `VLLM_CONFIGURE_LOGGING` is disabled and a value is given for
`VLLM_LOGGING_CONFIG_PATH`, an error will occur while starting vLLM.
### `VLLM_LOGGING_CONFIG_PATH`
`VLLM_LOGGING_CONFIG_PATH` allows users to specify a path to a JSON file of
alternative, custom logging configuration that will be used instead of vLLM's
built-in default logging configuration. The logging configuration should be
provided in JSON format following the schema specified by Python's [logging
configuration dictionary
schema](https://docs.python.org/3/library/logging.config.html#dictionary-schema-details).
If `VLLM_LOGGING_CONFIG_PATH` is specified, but `VLLM_CONFIGURE_LOGGING` is
disabled, an error will occur while starting vLLM.
## Examples
### Example 1: Customize vLLM root logger
For this example, we will customize the vLLM root logger to use
[`python-json-logger`](https://github.com/madzak/python-json-logger) to log to
STDOUT of the console in JSON format with a log level of `INFO`.
To begin, first, create an appropriate JSON logging configuration file:
**/path/to/logging_config.json:**
```json
{
"formatters": {
"json": {
"class": "pythonjsonlogger.jsonlogger.JsonFormatter"
}
},
"handlers": {
"console": {
"class" : "logging.StreamHandler",
"formatter": "json",
"level": "INFO",
"stream": "ext://sys.stdout"
}
},
"loggers": {
"vllm": {
"handlers": ["console"],
"level": "INFO",
"propagate": false
}
},
"version": 1
}
```
Next, install the `python-json-logger` package if it's not already installed:
```bash
pip install python-json-logger
```
Finally, run vLLM with the `VLLM_LOGGING_CONFIG_PATH` environment variable set
to the path of the custom logging configuration JSON file:
```bash
VLLM_LOGGING_CONFIG_PATH=/path/to/logging_config.json \
python3 -m vllm.entrypoints.openai.api_server \
--max-model-len 2048 \
--model mistralai/Mistral-7B-v0.1
```
### Example 2: Silence a particular vLLM logger
To silence a particular vLLM logger, it is necessary to provide custom logging
configuration for the target logger that configures the logger so that it won't
propagate its log messages to the root vLLM logger.
When custom configuration is provided for any logger, it is also necessary to
provide configuration for the root vLLM logger since any custom logger
configuration overrides the built-in default logging configuration used by vLLM.
First, create an appropriate JSON logging configuration file that includes
configuration for the root vLLM logger and for the logger you wish to silence:
**/path/to/logging_config.json:**
```json
{
"formatters": {
"vllm": {
"class": "vllm.logging.NewLineFormatter",
"datefmt": "%m-%d %H:%M:%S",
"format": "%(levelname)s %(asctime)s %(filename)s:%(lineno)d] %(message)s"
}
},
"handlers": {
"vllm": {
"class" : "logging.StreamHandler",
"formatter": "vllm",
"level": "INFO",
"stream": "ext://sys.stdout"
}
},
"loggers": {
"vllm": {
"handlers": ["vllm"],
"level": "DEBUG",
"propagage": false
},
"vllm.example_noisy_logger": {
"propagate": false
}
},
"version": 1
}
```
Finally, run vLLM with the `VLLM_LOGGING_CONFIG_PATH` environment variable set
to the path of the custom logging configuration JSON file:
```bash
VLLM_LOGGING_CONFIG_PATH=/path/to/logging_config.json \
python3 -m vllm.entrypoints.openai.api_server \
--max-model-len 2048 \
--model mistralai/Mistral-7B-v0.1
```
### Example 3: Disable vLLM default logging configuration
To disable vLLM's default logging configuration and silence all vLLM loggers,
simple set `VLLM_CONFIGURE_LOGGING=0` when running vLLM. This will prevent vLLM
for configuring the root vLLM logger, which in turn, silences all other vLLM
loggers.
```bash
VLLM_CONFIGURE_LOGGING=0 \
python3 -m vllm.entrypoints.openai.api_server \
--max-model-len 2048 \
--model mistralai/Mistral-7B-v0.1
```
## Additional resources
- [`logging.config` Dictionary Schema Details](https://docs.python.org/3/library/logging.config.html#dictionary-schema-details)
examples/lora_with_quantization_inference.py 0 → 100644
View file @ 62f68735
"""
This example shows how to use LoRA with different quantization techniques
for offline inference.
Requires HuggingFace credentials for access.
"""
import gc
from typing import List, Optional, Tuple
import torch
from huggingface_hub import snapshot_download
from vllm import EngineArgs, LLMEngine, RequestOutput, SamplingParams
from vllm.lora.request import LoRARequest
def create_test_prompts(
lora_path: str
) -> List[Tuple[str, SamplingParams, Optional[LoRARequest]]]:
return [
# this is an example of using quantization without LoRA
("My name is",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128), None),
# the next three examples use quantization with LoRA
("my name is",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128),
LoRARequest("lora-test-1", 1, lora_path)),
("The capital of USA is",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128),
LoRARequest("lora-test-2", 1, lora_path)),
("The capital of France is",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128),
LoRARequest("lora-test-3", 1, lora_path)),
]
def process_requests(engine: LLMEngine,
test_prompts: List[Tuple[str, SamplingParams,
Optional[LoRARequest]]]):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
while test_prompts or engine.has_unfinished_requests():
if test_prompts:
prompt, sampling_params, lora_request = test_prompts.pop(0)
engine.add_request(str(request_id),
prompt,
sampling_params,
lora_request=lora_request)
request_id += 1
request_outputs: List[RequestOutput] = engine.step()
for request_output in request_outputs:
if request_output.finished:
print("----------------------------------------------------")
print(f"Prompt: {request_output.prompt}")
print(f"Output: {request_output.outputs[0].text}")
def initialize_engine(model: str, quantization: str,
lora_repo: Optional[str]) -> LLMEngine:
"""Initialize the LLMEngine."""
if quantization == "bitsandbytes":
# QLoRA (https://arxiv.org/abs/2305.14314) is a quantization technique.
# It quantizes the model when loading, with some config info from the
# LoRA adapter repo. So need to set the parameter of load_format and
# qlora_adapter_name_or_path as below.
engine_args = EngineArgs(
model=model,
quantization=quantization,
qlora_adapter_name_or_path=lora_repo,
load_format="bitsandbytes",
enable_lora=True,
max_lora_rank=64,
# set it only in GPUs of limited memory
enforce_eager=True)
else:
engine_args = EngineArgs(
model=model,
quantization=quantization,
enable_lora=True,
max_loras=4,
# set it only in GPUs of limited memory
enforce_eager=True)
return LLMEngine.from_engine_args(engine_args)
def main():
"""Main function that sets up and runs the prompt processing."""
test_configs = [{
"name": "qlora_inference_example",
'model': "huggyllama/llama-7b",
'quantization': "bitsandbytes",
'lora_repo': 'timdettmers/qlora-flan-7b'
}, {
"name": "AWQ_inference_with_lora_example",
'model': 'TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ',
'quantization': "awq",
'lora_repo': 'jashing/tinyllama-colorist-lora'
}, {
"name": "GPTQ_inference_with_lora_example",
'model': 'TheBloke/TinyLlama-1.1B-Chat-v0.3-GPTQ',
'quantization': "gptq",
'lora_repo': 'jashing/tinyllama-colorist-lora'
}]
for test_config in test_configs:
print(
f"~~~~~~~~~~~~~~~~ Running: {test_config['name']} ~~~~~~~~~~~~~~~~"
)
engine = initialize_engine(test_config['model'],
test_config['quantization'],
test_config['lora_repo'])
lora_path = snapshot_download(repo_id=test_config['lora_repo'])
test_prompts = create_test_prompts(lora_path)
process_requests(engine, test_prompts)
# Clean up the GPU memory for the next test
del engine
gc.collect()
torch.cuda.empty_cache()
if __name__ == '__main__':
main()
examples/multilora_inference.py 0 → 100644
View file @ 62f68735
"""
This example shows how to use the multi-LoRA functionality
for offline inference.
Requires HuggingFace credentials for access to Llama2.
"""
from typing import List, Optional, Tuple
from huggingface_hub import snapshot_download
from vllm import EngineArgs, LLMEngine, RequestOutput, SamplingParams
from vllm.lora.request import LoRARequest
def create_test_prompts(
lora_path: str
) -> List[Tuple[str, SamplingParams, Optional[LoRARequest]]]:
"""Create a list of test prompts with their sampling parameters.
2 requests for base model, 4 requests for the LoRA. We define 2
different LoRA adapters (using the same model for demo purposes).
Since we also set `max_loras=1`, the expectation is that the requests
with the second LoRA adapter will be ran after all requests with the
first adapter have finished.
"""
return [
("A robot may not injure a human being",
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128), None),
("To be or not to be,",
SamplingParams(temperature=0.8,
top_k=5,
presence_penalty=0.2,
max_tokens=128), None),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\n question: Name the ICAO for lilongwe international airport [/user] [assistant]", # noqa: E501
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora", 1, lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]", # noqa: E501
SamplingParams(n=3,
best_of=3,
use_beam_search=True,
temperature=0,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora", 1, lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_74 (icao VARCHAR, airport VARCHAR)\n\n question: Name the ICAO for lilongwe international airport [/user] [assistant]", # noqa: E501
SamplingParams(temperature=0.0,
logprobs=1,
prompt_logprobs=1,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora2", 2, lora_path)),
(
"[user] Write a SQL query to answer the question based on the table schema.\n\n context: CREATE TABLE table_name_11 (nationality VARCHAR, elector VARCHAR)\n\n question: When Anchero Pantaleone was the elector what is under nationality? [/user] [assistant]", # noqa: E501
SamplingParams(n=3,
best_of=3,
use_beam_search=True,
temperature=0,
max_tokens=128,
stop_token_ids=[32003]),
LoRARequest("sql-lora", 1, lora_path)),
]
def process_requests(engine: LLMEngine,
test_prompts: List[Tuple[str, SamplingParams,
Optional[LoRARequest]]]):
"""Continuously process a list of prompts and handle the outputs."""
request_id = 0
while test_prompts or engine.has_unfinished_requests():
if test_prompts:
prompt, sampling_params, lora_request = test_prompts.pop(0)
engine.add_request(str(request_id),
prompt,
sampling_params,
lora_request=lora_request)
request_id += 1
request_outputs: List[RequestOutput] = engine.step()
for request_output in request_outputs:
if request_output.finished:
print(request_output)
def initialize_engine() -> LLMEngine:
"""Initialize the LLMEngine."""
# max_loras: controls the number of LoRAs that can be used in the same
# batch. Larger numbers will cause higher memory usage, as each LoRA
# slot requires its own preallocated tensor.
# max_lora_rank: controls the maximum supported rank of all LoRAs. Larger
# numbers will cause higher memory usage. If you know that all LoRAs will
# use the same rank, it is recommended to set this as low as possible.
# max_cpu_loras: controls the size of the CPU LoRA cache.
engine_args = EngineArgs(model="meta-llama/Llama-2-7b-hf",
enable_lora=True,
max_loras=1,
max_lora_rank=8,
max_cpu_loras=2,
max_num_seqs=256)
return LLMEngine.from_engine_args(engine_args)
def main():
"""Main function that sets up and runs the prompt processing."""
engine = initialize_engine()
lora_path = snapshot_download(repo_id="yard1/llama-2-7b-sql-lora-test")
test_prompts = create_test_prompts(lora_path)
process_requests(engine, test_prompts)
if __name__ == '__main__':
main()
examples/offline_inference.py 0 → 100644
View file @ 62f68735
from vllm import LLM, SamplingParams
if __name__ == '__main__':
# Sample prompts.
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=16)
# Create an LLM.
llm = LLM(model="facebook/opt-125m",tensor_parallel_size=1, distributed_executor_backend="ray", dtype="float16",trust_remote_code=True, enforce_eager=True)
# Generate texts from the prompts. The output is a list of RequestOutput objects
# that contain the prompt, generated text, and other information.
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment