GitLab

* Attempt for cleverer auto batch_prefill values (some simplifications).

* Less flaky tests.

* Fixing typo insertion.

* Update launcher/src/main.rs
Co-authored-by: Daniël de Kok <me@danieldk.eu>

* Adding small comment for source of calculation.

* Adding L40.

* Adding L40s.

---------
Co-authored-by: Daniël de Kok <me@danieldk.eu>

* Attempt at automatic max batch prefill.

* Taking into account number of shards.

* Adding more cards.

* Adding A100 + H100

* Adding a few more cards.

* Logprobs cost too much.

* h100 better name, and keep factor of 2

* Damn inflated sparse tflops.

* Typo in h100.

* Updated the flops calculation (checked with fvcore).

* chunking by default.

* Fix prefix caching for chat completion since we removed logprobs.

* More tests.

* Dropping all the prefill logprobs.

* Add a flag that enables users to get logprobs back.

* Repairing prompt token counting.

* Fixing a few tests.

* Remove some scaffolding.

* Attempting to reduces the issues (workarounds for now).

* feat: add payload limit

* update launcher

compressed-tensors is a safetensors extension for sparse, quantized
tensors. The format is more powerful than earlier AWQ/GPTQ/FP8
quantization, because

- Different quantizer configurations can be used for different targets.
- The format can specify input/output quantizers in addition to weight
  quantizers.
- Configurable exclusions for quantization.

This change adds a dependency on the `compressed-tensors` package for
its configuration parsing and layer matching functionality.

The following types of quantization are supported in this PR:

- W8A16 and W4A16 INT using GPTQ-Marlin kernels.
- W8A8 and W8A16 FP using FP8-Marlin and cutlass kernels.

Support for other quantization types will be added in subsequent PRs.

* Choosing input/total tokens automatically based on available VRAM?

* Update doc.

* Remove generated files.

* Trying to fix non chunking targets.

* Attempt #2

* fix.

* QuantLinear is rocm compatible.

* Much simpler logic after the overhead.

* Updating logic + non flash.

* Revert doc text.

* Simple updates.

* Fix integration mt0 (transformers update).

specifiying a value.

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

* 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>

* 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>

* Add basic FP8 KV cache support

This change adds rudimentary FP8 KV cache support. The support is
enabled by passing `--kv-cache-dtype fp8_e5m2` to the launcher. Doing so
uses this type for the KV cache. However support is still limited:

* Only the `fp8_e5m2` type is supported.
* The KV cache layout is the same as `float16`/`bfloat16` (HND).
* The FP8 KV cache is only supported for FlashInfer.
* Loading of scales is not yet supported.

* Fix Cargo.toml

allow revision for lora adapters from launcher
Co-authored-by: Sida <sida@kulamind.com>
Co-authored-by: teamclouday <teamclouday@gmail.com>

Remove compute capability lock

We are only calling the `get_cuda_capability` function once, so avoiding
the cost of multiple calls is not really necessary yet.

* Improve support for GPUs with capability < 8

- For models that cannot use flashinfer, use flash-attn v1 + paged
  attention for models with a compute capability older than 8.
- Disable prefix caching when using paged attention.
- When using flash-attn v1, pass the key/value, rather than the
  cache, since v1 cannot use block tables.

* nix: add flash-attn-v1 to the server environment

* Move disabling prefix caching into the block of exceptions

* Capability as `usize`s

* fix: wrap python basic logs in debug assertion in launcher

* use level filters instead

* Adding prefix test.

* [WIP] tmp dump of integration load tests.

* Remove other tensor creation.

* Fixed the radix tree.

Used a slice everywhere in radix.rs to keep the cheap Arc cloning
instead of recomputing the input_ids.

* Fix parsing

* Is it really flashinfer version ?

* Remove some comments.

* Revert the max prefix hit.

* Adding numpy to diff.

* Upgraded flashinfer.

* Upgrading some stuff.

* Are we done yet ?

* Minor fixup

* Remove 1 log and put back the other.

* Add comment for why slot 0 is OK.

* Mounting on the job.

* Get me a debug branch

* Debugging CIs is fun.

* Attempt #28

* wip

* Tmate.

* Praying.

* Updating VLM causal model with updated context.

* Important line got squashed.

* Tmate again.

* Fingers crossed.

* We want only 1 run of integration tests.....

---------
Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>

* Making prefix/flashinfer the default and testing the full release tests.

* Include flashinfer in the docker.

* Using prebuilt.

* Allowing window_left_size (dummy version).

* Disabling flashinfer/prefix caching on odd head_dim

* Disable prefix caching for lora.

* More specific codes.

* Update lock

* Updating integration tests with new values with FI/FD.

Remove paged as a default too, and using FD everywhere.

* Update cargo lock ?

* Upgrade to 1.80 because of bitstream...

* Everywhere 1.80

* Forgot last default place.

* Apply suggestions from code review
Co-authored-by: drbh <david.richard.holtz@gmail.com>

* Updated flake lock

* Tmp

* Upgrade resolution system for less errors in resolution.

* Remove lambda for cleaner function.

* Handling debugger.

* OVerride the env in server tests.

* Is this enough to make it work ?

* This seems to be working.

* Downgrade some logs.

* Fixing the default for vlm.

* Don't enable prefix caching on VLM just yet.

* Change `add_special_tokens` in order to have the correct tokens for chat
input and not (since it's super important with the prefixing now)

* Fixing prefix caching for flashdecoding.

* Update all models.

* Fixed flashinfer version.

* add_special_tokens is internal only

* Fixing seqlen with the new vlms.

* Fixing the issue with `add_special_tokens` not being passed around.

* Fixing the test.

* Removing encoder_decoder (seq2seq).

* Update the chat test.

* Fixing the batching tokenization in flash causal lm.

* Truncating left for radix purposes.

* Oops this doesn't belong here.

* Put back default pure shell.

* Update server tests

- Default to throughput test in k6
- Use TGI_WIGGLE_ROOM to adjust wiggle room

* Only n_heads / process_group.size() are necessary.

* Revert the integrationt tests change (seem linked to head_size
modification).

* Adding error message when assert is violated.

* Fixing the free algorithm to handle times where the common prefix is
smaller.

* Apply suggestions from code review
Co-authored-by: OlivierDehaene <olivier@huggingface.co>

* Update server/text_generation_server/layers/attention/common.py
Co-authored-by: OlivierDehaene <olivier@huggingface.co>

* Fix disabling prefix caching - Fix windowing checks.

* Revert the Cohere tokenizer change (for now using a revision instead).

* Fmt.

---------
Co-authored-by: drbh <david.richard.holtz@gmail.com>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>

* Fixing exl2 and other quanize tests again.

* Mark exl2 as non release (so CI tests them, needs to be removed latet).

* Fixing exl2 (by disabling cuda graphs)

* Fix quantization defaults without cuda graphs on exl2 (linked to new
issues with it).

* Removing serde override.

* Go back to released exl2 and remove log.

* Adding warnings for deprecated bitsandbytes + upgrade info to warn.

* Using an enum for flash backens (paged/flashdecoding/flashinfer)

* Early exit on server too.

* Clippy.

* Fix clippy and fmt.

* refactor usage stats

* Update docs/source/usage_statistics.md
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* Update router/src/server.rs
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* changes based on feedback

* run python3 udpate_doc.py

* fix pre-commit

* Update router/src/server.rs
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>

* delete option around usage stats arg

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

* Add API_Key for Auth and conditionally add authorisation for non info/health endpoints.

* change name to info routes

* Fix comment

* convert strings to lowercase for case insensitive comparison

* convert header to string

* fixes and update docs

* update docs again

* revert wrong update

---------
Co-authored-by: Kevin Duffy <kevin.duffy94@gmail.com>

* fix: refactor adapter weight loading and mapping

* feat: enable lora load from directory

* fix: adjust launcher for local lora adapters

* feat: improve weight loading and add tests

* fix: improve logging and rebase syntax issue

* fix: impove adapter merge comments and remove unused conditional

* fix: improve get_model_with_lora_adapters naming

* fix: comment typo

* Preparing for release.

* Updating docs.

* Fixing token within the docker image for the launcher.

* Softcapping for gemma2.

* Less clutter.

* No access to transformers config, only config_dict here.

* 0.0 is the null value in the C++ API.

* draft of usage stats

* fix wrong link

* launcher doesn't need sysinfo dep

* only tokenizer class instead of hole struct

* unused import

* fix clippy errors

* update openAPI doc

* cargo fmt

* fix error in passing flags to router

* try again to update docs

* run pre-commit locally

* Update router/src/main.rs
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>

* Update router/src/main.rs
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>

* on crash use anonymous error event

* delete json_output and ngrok

* more robust way of checking if is in container

* more robust nvidia smi

* parse xpu more robustly

* fix errors

* add nvidia-smi details in docs

* cargo fmt

* fix clippy

* should make docs check pass

* Update router/src/usage_stats.rs
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>

* error reason can't be in nested json

* cargo fmt

---------
Co-authored-by: Hugo Larcher <hugo.larcher@huggingface.co>
Co-authored-by: Erik Kaunismäki <erikkaum@Eriks-MacBook-Pro.local>

* feat: first draft load multiple lora

* feat: load weights within layer and refactor lora pass

* fix: refactor and reduce lora math

* feat: baseline impl single request multi lora support

* feat: prefer lorax implementation and port loading logic

* fix: prefer adapter_data and refactors

* feat: perfer loraxs custom punica kernels and add mlp loras

* fix: adjust batch for bgmv

* fix: adjust adapter_segments logic when in batch

* fix: refactor and move changes to v3 proto

* fix: pass model_id for all flash causal lms

* fix: pass model_id for all causal and seq2seq lms

* fix: add model_id to model test

* feat: add lora support to mistral and refactors

* feat: prefer model id in request

* fix: include rust code for adapter id

* feat: bump launcher and add new lora docs

* feat: support base model generation and refactors

* fix: rename doc to retry ci build

* feat: support if vlm models

* fix: add adapter_data param and avoid missing layers

* fix: add adapter_data param to phi and neox

* fix: update all models forwards to include adapter_data

* fix: add model_id to IdeficsCausalLM

* Update lora.md

Fixed a typo

* Update lora.md

Fixing spam image

* fix: add lora kernel to dockerfile, support running without kernels and refactors

* fix: avoid dockerfile conflict

* fix: refactors and adjust flash llama lora logic

* fix: skip llama test due to CI issue (temp)

* fix: skip llama test CI (temp) 2

* fix: revert skips and prefer updated ci token for tests

* fix: refactors and helpful comments

* fix: add noop in TensorParallelAdapterRowLinear too

* fix: refactor and move shard_lora_weights logic

* fix: exit early if no adapter_data

---------
Co-authored-by: Derek <datavistics@gmail.com>

Fix clippy.

* use xpu-smi to dump used memory
xpu use "ZE_AFFINITY_MASK" to control card, usage is like CUDA_VISIBLE_DEVICES
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* Update server/text_generation_server/utils/import_utils.py
Co-authored-by: Daniël de Kok <me@github.danieldk.eu>

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Daniël de Kok <me@github.danieldk.eu>

* Adding Service Name Environment variable for https://github.com/huggingface/text-generation-inference/issues/2069

* Update Docs

* Update README.md

* Update Launcher Docs

* Update Launcher Docs
Removing Option

* Support HF_TOKEN environement variable

* Load test.

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

* update vllm commit & fix models using sliding window

* update

* update commit

* fix bug where tunableop is bound to cuda graph even when cuda graph are disabled

* enable tunableop by default

* fix sliding window

* address review

* dead code

* precise comment

* is it flaky?

This change adds support for Marlin-quantized models. Marlin is an
FP16xINT4 matmul kernel, which provides good speedups decoding batches
of 16-32 tokens. It supports quantized models with symmetric
quantization, groupsize -1 or 128, and 4-bit.

Tested with:

- Llama 2
- Llama 3
- Phi 3

# What does this PR do?

I think this will fix the docs from being weirdly formatted. All the
sections after MAX_TOP_N_TOKENS don't show up in the bar on the right
(https://huggingface.co/docs/text-generation-inference/basic_tutorials/launcher#maxtopntokens)


## Before submitting
- [x] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Did you read the [contributor
guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests),
      Pull Request section?
- [ ] Was this discussed/approved via a Github issue or the
[forum](https://discuss.huggingface.co/)? Please add a link
      to it if that's the case.
- [ ] Did you make sure to update the documentation with your changes?
Here are the
[documentation
guidelines](https://github.com/huggingface/transformers/tree/main/docs),
and
[here are tips on formatting
docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation

).
- [ ] Did you write any new necessary tests?


## Who can review?

@merveenoyan

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

Mostly straightforward, changes to existing code:

* Wrap quantizer parameters in a small wrapper to avoid passing
  around untyped tuples and needing to repack them as a dict.
* Move scratch space computation to warmup, because we need the
  maximum input sequence length to avoid allocating huge
  scratch buffers that OOM.