GitLab

specifiying a value.

* Add support for FP8 KV cache scales

Since FP8 only has limited dynamic range, we can scale keys/values
before storing them into the cache (and unscale them in attention). To
avoid rescaling the cache as the absmax values change, good scales are
usually determined per layer using calibration calibration data and stored
in the checkpoint.

This change adds support for for using key-value scales and loading them
from checkpoints in the two most common formats:

- Separate per-layer `k_scale` and `v_scale` scalars.
- Per-layer `kv_scale` scalar (older format).

Currently, scales are only used with an `float8_e4m3fn` cache.

Besides adding support for key/value scales, the `fp8_quantize` function
is also extended to support quantization with a kernel vendored from
vLLM. This is slightly faster than the PyTorch implementation, but also
scales in FP32, potentially improving accuracy.

* Update FP8 KV cache test to use checkpoint with scales

* `can_scale`: check that the attention is flashinfer

PR #2682 also fixed in issue in Phi MoE, but it changes the test
outputs a bit. Fix this.

* feat: allow any supported payload on /invocations

* update openAPI

* update doc

* feat: natively support Granite models

* Update doc

* Add `impureWithCuda` dev shell

This shell is handy when developing some kernels jointly with TGI - it
adds nvcc and a bunch of commonly-used CUDA libraries to the environment.

We don't add this to the normal impure shell to keep the development
environment as clean as possible (avoid accidental dependencies, etc.).

* Add cuDNN

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

Update the Mixtral GPTQ test to use a model with `desc_act=true` and
`group_size!=-1` to ensure that we are checking activation
sorting/non-full K (with tensor parallelism). The `desc_act=false` case
is already checked by the Mixtral AWQ test.

Change `fp8_quantize` so that we can pass around reciprocals everywhere,
so scales are always passed around in the checkpoint format.

I also noticed that we ignore any input scales that we might have when
fbgemm is available. Skip this path if we already have a scale.

* add gptq and awq int4 support in intel platform
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix ci failure
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* set kv cache dtype
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* refine the code according to the review command
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Simplifying conditionals + reverting integration tests values.

* Unused import

* Fix redundant import.

* Revert change after rebase.

* Upgrading the tests (TP>1 fix changes to use different kernels.)

* Update server/text_generation_server/layers/gptq/__init__.py

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Wang, Yi A <yi.a.wang@intel.com>

* fix: prefer inplace softmax to avoid copy

* Update server/text_generation_server/models/flash_causal_lm.py
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

tgi-entrypoint: exec instead of spawning a child process

reason: otherwise parent will receive the signals when we'd like tgi to receive them
keeping the parent/child is not necessary and would require the parent to handle signals to forward them properly to the child
Signed-off-by: Raphael Glon <oOraph@users.noreply.github.com>
Co-authored-by: Raphael Glon <oOraph@users.noreply.github.com>

* Simplify the `attention` function

- Use one definition rather than multiple.
- Add `key`/`value` arguments, so that we don't need the
  `PREFILL_IN_KVCACHE` constant.
- Make it kwargs-only (to avoid mixing up the various `Tensor` args).

* Fixup flashinfer support

* Support `e4m3fn` KV cache

* Make check more obvious

* wip

* rollback

* refactor to use prefix/postfix namming + fix all_input_ids_tensor

* maybe patching vlms?

* fix filter and concat

* wip, no filter, no concat

* current

* add prepare_for_prefill

* working

* load tested

* re-create slots

* re-create slots

* fix slot_filtering_indices

* feedback loop

* remove log

* fix benchmarker

* fix vlm and seq2seq

* rename to cache and input lengths

* fix prefill logprobs

* fix launcher

* fix logprobs?

* idk at this point

* max input length

* omfg

* remove debugging lines

* fix tests

* fix mllama

* fix cargo tests

* remove support chunking for paged

* Fixing non blocked attentions

* Fixing dtype + AMD, Ipex targets.

* lint fix.

* rename

* Fix prefix_caching variable, remove defaults in server (confusing a lot
of the times).

* Add simple resolution when user specifies ATTENTION=paged.

* Put back non default simple tests.

* Fix env name

---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* (feat) fp8 fnuz support for rocm

* (review comments) Fix compression_config load, type hints

* (bug) update all has_tensor

* (review_comments) fix typo and added comments

* (nit) improved comment

As spotted by @philschmid, the payload was compliant with Vertex AI, but
just partially, since ideally the most compliant version would be with
the generation kwargs flattened to be on the same level as the
`messages`; meaning that Vertex AI would still expect a list of
instances, but each instance would be an OpenAI-compatible instance,
which is more clear; and more aligned with the SageMaker integration
too, so kudos to him for spotting that; and sorry from my end for any
inconvenience @Narsil.

XPU backend is available natively (without IPEX) in pytorch starting
from pytorch 2.4. This commit extends TGI to cover the case when user
has XPU support thru pytorch 2.4, but does not have IPEX installed.
Models which don't require attention can work. For attention required
models more work is needed to provide attention implementation.

Tested with the following models:
* teknium/OpenHermes-2.5-Mistral-7B
* bigscience/bloom-560m
* google/gemma-7b
* google/flan-t5-xxl
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

Update quicktour.md

* break when there's nothing to read
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Different approach, only listen on stdin when `LOG_LEVEL=debug` (which
is where dropping to a debugger is important).

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Wang, Yi A <yi.a.wang@intel.com>

* Small improvements for docs

* Update _toctree.yml

* Updating the doc (we keep the list actually).

---------
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* Intel CI ?

* Let's try non sharded gemma.

* Snapshot rename

* Apparently container can be gone already.

Update to most recent stable version of TGI.

* feat: process token stream before returning to client

* fix: expect content in test

* fix: improve comparison via ruff lint

* fix: return event in all cases

* fix: always send event on error, avoid unwraps, refactor and improve tests

* fix: prefer no_tool over notify_error to improve reponse

* fix: adjust chat input test for no_tool

* fix: adjust test expected content

---------
Co-authored-by: System administrator <root@ip-10-90-0-186.ec2.internal>

* Only run 1 valid test.

* TRying the tailscale action quickly.

* ?

* bash spaces.

* Remove tailscale.

* More quotes.

* mnt2 ?

* Othername to avoid recursive directories.

* Good old tmate.

* Remove tmate.

* Trying a few things.

* Remove some stuff.

* Sleep ?

* Tmp

* busybox

* Launcher tgi

* Starting hello

* Busybox in python

* No device.

* Removing all variables ?

* A un moment donné.

* Tmp

* Tmp2

* DEvice request, no container name

* No device requests

* Without pytest.

* No pytest.

* from env

* Start with devices

* Attemp #1

* Remove stdin messing

* Only 1 test, no container name

* Raw tgi

* Sending args.

* Show pip freeze.

* Start downloading with token

* Giving HIP devices.

* Mount volume + port forward

* Without pytest.

* No token

* Repeated arguments

* Wrong kwarg.

* On 2 GPUs

* Fallback to single shard CI test.

* Testing

* yaml

* Common cache ?

* Trailing slash ?

* Docker volume split.

* Fix docker volume

* Fixing ?

* ?

* Try no devices ?

* Flash llama on intel CPU ?

* Fix nvidia ?

* Temp deactivate intel, activate nvidia ?

To make sure that everything is formatted with the same black version
as CI.

I sometimes use isort for new files to get nicely ordered imports,
so add it as well. Also set the isort configuration to format in a
way that is compatible with black.

* Update ToolType input schema

* lint

* fix: run formatter

* fix: allow tool choide to be null

---------
Co-authored-by: Wauplin <lucainp@gmail.com>

* Add support for fused MoE Marlin for AWQ

This uses the updated MoE Marlin kernels from vLLM.

* Add integration test for AWQ MoE

* Upgrade minor rust version (Fixes rust build compilation cache)

* Black

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

Update kv_cache.py