GitLab

* feat: add payload limit

* update launcher

* feat: Add automatic nightly benchmarks

* fix: Update runners group

* fix: add created_at field to results

* fix: Add variable results file location

fix: incomplete generations w/ single tokens generations and models that did not support chunking (#2770)

* Incomplete generation stream fix (#2754)

entries.len() could > batch.size in prefill, so need to filter as well.
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* entries was wrongly extended for model that did not support chunking

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

fix: set outlines version to 0.1.3 to avoid bug

* nix: build and cache all devshells

* nix: add poetry to the impure shell

This shouldn't be used to manage dependencies in a Nix devshell, but can
be handy to update `poetry.lock`.

* Fix Nix build, disable pure shell (covered by Nix tests)

This change adds support for wNa16 int checkpoints with 2:4 sparsity
using Marlin 2:4 kernels.

* add OpenAI like tool_choice for named choice

* add tests

* fix: run linter and bump api docs

* fix: consolidate changes and remove old tool type

* feat: improve, simplify and rename tool choice struct add required support and refactor

* fix: simplify tool choice logic, improve tests, openapi and rust docs

* fix: refactor away prepare_chat_input and improve tool grammar apply control flow

* feat: update docs and add tool choice configuration section

* fix: simplify naming, tool choice default and improve test

* fix: adjust tool choice none logic, add test and small refactors

* fix: add missing snapshot file

* fix: adjust tool choice type in test

* fix: adjust default when json tool choice is

* fix: remove trailing space lint after rebase

* fix: remove mostly mocked unit test

---------
Co-authored-by: Linus Bierhoff <linus.bierhoff@icloud.com>

This version syncs with the vLLM kernels and brings some performance
improvements.

* feat: support flash attention 2 in qwen2 vl vision blocks

* fix: calc max_seqlen once and small refactors

* Add support for compressed-tensors w8a8 int checkpoints

This change adds a loader for w8a8 int checkpoints. One large benefit of
int8 support is that the corresponding cutlass matmul kernels also work on
compute capability 7.5.

Evaluation on neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a8:

|     Tasks     |Version|     Filter     |n-shot|        Metric         |   |Value |   |Stderr|
|---------------|------:|----------------|-----:|-----------------------|---|-----:|---|------|
|gsm8k_cot_llama|      3|flexible-extract|     8|exact_match            |↑  |0.8431|±  |0.0100|
|               |       |strict-match    |     8|exact_match            |↑  |0.8393|±  |0.0101|
|ifeval         |      4|none            |     0|inst_level_loose_acc   |↑  |0.8597|±  |   N/A|
|               |       |none            |     0|inst_level_strict_acc  |↑  |0.8201|±  |   N/A|
|               |       |none            |     0|prompt_level_loose_acc |↑  |0.7967|±  |0.0173|
|               |       |none            |     0|prompt_level_strict_acc|↑  |0.7468|±  |0.0187|

Which is the same ballpark as vLLM.

As usual, lots of thanks to Neural Magic/vLLM for the kernels.

* Always use dynamic input quantization for w8a8 int

It's far less flaky and gives better output.

* Use marlin-kernels 0.3.5

* Fix a typo
Co-authored-by: drbh <david.richard.holtz@gmail.com>

* Small fixes

---------
Co-authored-by: drbh <david.richard.holtz@gmail.com>

* add ipex moe implementation to support Mixtral and PhiMoe
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* update to ipex xpu 2.5
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* torch has xpu support in 2.5
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

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

* Apply suggestions from code review
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>

* Remove vLLM dependency for CUDA

This change adds `attention-kernels` as a dependency for paged
attention and cache reshaping. With that, we don't use vLLM
anywhere for CUDA.

Tested run (since we don't have paged attention in CI):

```
❯ ATTENTION=paged python -m pytest integration-tests -k "llama and awq" --release
[...]
5 snapshots passed.
```

* Fix clippy warning

* feat: return streaming errors as an event formatted for openai's client

* fix: propagate completions error events to stream

* fix: improve stream api error format and add status code

* fix: improve streamin error to include error_type

* Revert "fix: improve streamin error to include error_type"

This reverts commit 2b1a360b1511d94ea9a24e5432e498e67939506a.

* Reworked the implementation.

* Revert "Reworked the implementation."

This reverts commit 7c3f29777f17411ae4ade57e2f88e73cde704ee5.

* Small lifting.

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

* Upgrading our deps.

* fixup.

* Fixup.

* Upgrade outlines to 0.1.1

* Update for new API

* Check if allowed tokens is None

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

Signed-off-by: jitokim <pigberger70@gmail.com>

fix: change embeddings to embedding
Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-135.us-west-2.compute.internal>

Co-authored-by: Ubuntu <ubuntu@ip-172-31-28-135.us-west-2.compute.internal>

Updates from Triton 2.1.0 to 3.1.0 (among other things).

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.

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

fix incorrect output of Qwen2-7B-Instruct-GPTQ-Int4 and Qwen2-7B-Instruct-AWQ
ipex kernel provide func like add_bias, so no need add it outside
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix: create position ids for text only input

* fix: prefer repeat over expand to avoid clone

* feat: support multidimensional position ids on batch to enable cuda graphs on qwen2-vl

* fix: only check model type if config exists

* fix: adjust sharding and lm head logic

* fix qwen2 failure in intel cpu
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* fix: return correct shape logits and add streaming test

* fix: remove unused import and refactor test

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

* feat: add support for qwen2 vl model

* feat: fix token padding, enable warmup and process basic request

* fix: improve get_position_ids, add lift embed_tokens

* fix: remove get_cos_sin_hack dev function

* feat: add simple test chat with meesage and text

* fix: lint test

* fix: adjust positional embeddings for multi dimensional position ids

* fix: update docs and lint unused vars

* fix: include linted file

* fix: add norm after text output

* fix: format model file

* fix: adjust for ruff lints

* fix: remove unused rotate_half

* feat: refactors and calc num features

* fix: prefer position_ids passed from vlm causal lm and reset ids on batch

* fix: adjust get_position_ids if not available and add required args to signatures

* fix: adjust resize case for qwen2_vl warmup

* fix: avoid qwen2 vl specific paths with qwen2