GitLab

This change adds support for 2:4 sparsity when using Marlin
quantization. The 2:4 kernel is used when:

* The quantizer is `marlin`;
* the quantizer checkpoint format is `marlin_24`.

Fixes #2098.

When the AWQ quantizer was used with a layer that uses a bias,
the bias tensor was not correctly passed/used. Instead, the
value `true`/`1.0` was added to the linear transformation.

Correctly pass through the bias when it is not `None`.

Fixes #2106.

* 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.

* Add pytest release marker

Annotate a test with `@pytest.mark.release` and it only gets run
with `pytest integration-tests --release`.

* Mark many models as `release` to speed up CI

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

* Removing IPEX_AVAIL.

Chose to unify CPU and XPU under `ipex`. Most code is exactly similar
except for a very few spots.

The biggest number of spots is the kv-cache layout and the flash_xxx.py
files.
Since those files should be removed soon and factored away, we should
not need them.

* Forgot a few places.

* Unrelated change.

* Fixing HF_TOKEN.

* HF_TOKEN

* feat: add simple tests for weights

* fix: adjust types and add tests

* fix: adjust so all tests pass

* feat: improve weight tests

* fix: add missing tests and renames

* fix: tweak shapes

* add CPU tgi support
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

* ipex distributed ops support
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>

---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Funtowicz Morgan <mfuntowicz@users.noreply.github.com>

fix ChatCompletion and ChatCompletionChunk object string not compatible with standard openai api (#2089)
Co-authored-by: sunxichen <sun.xc@digitalcnzz.com>

* 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>

* corrected Pydantic warning.

* Update clients/python/text_generation/types.py
Co-authored-by: Daniël de Kok <me@github.danieldk.eu>

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

* Fix cargo-chef prepare

In prepare stage, cargo-chef reads Cargo.lock and transforms it accordingly.
If Cargo.lock is not present, cargo-chef will generate a new one first, which
might vary a lot and invalidate docker build caches.

* Fix Dockerfile_amd and Dockerfile_intel

* New runner. Manual squash.

* Network host.

* Put back trufflehog with proper extension.

* No network host ?

* Moving buildx install after tailscale ?

* 1.79

The subcommand did not work due to some broken imports.

For Phi-3-Small I need to shard a packed QKV bias tensor, for which
I implemented the `Weights.get_packed_sharded` method. However, this
method can also replace the `Weights._get_qweight` method and the
custom sharding code from `Weights.get_weights_col_packed`.

Fixes #2081.

* test local tailscale

* Update build.yaml

* Update build.yaml

* Update build.yaml

* Update build.yaml

* wait for ssh

* network host

* change step order

* Set maximum grpc message receive size to 2GiB

The previous default was 4MiB, which doesn't really work well for
multi-modal models.

* Update to Rust 1.79.0

* Fixup formatting to make PR pass

* Contributing guide & Code of Conduct

* Redirect to GitHub's tutorial on PRs

When a batch contained images if different sizes during prefill, the
server would fail (see e.g. #2056). Images were processed separately and
then concatenated. However, this can fail for images with different sizes.

Fix this by preprocessing all images in the batch together, so that the
image processor can ensure that all image tensors have compatible sizes.

* doc: adding architecture document

* doc: add architecture to toctree

* fix: avoid cargo lock changes

* fix: avoid cargo lock tweak

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

* Update the link for qwen2

* Fix Qwen2 model URL in model table

* Fix too eager staging

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

Add support for GPTQ Marlin kernels

GPTQ Marlin extends the Marlin kernels to support common GPTQ
configurations:

- bits: 4 or 8
- groupsize: -1, 32, 64, or 128
- desc_act: true/false

Using the GPTQ Marlin kernels requires repacking the parameters in the
Marlin quantizer format.

The kernels were contributed by Neural Magic to VLLM. We vendor them
here for convenience.

* feat: add kserve feature and basic routes

* feat: implement infer endpoint wrapper around generate

* fix: refactor and improve types

* fix: improve infer and simplify

* fix: cleanup and improve api docs

* fix: refactor and encapsulate kserve feat in file

* fix: remove typos after rebase

* Use minijinja's pycompat mode for python methods

* fix: cargo fmt lint for pre commit

---------
Co-authored-by: Armin Ronacher <armin.ronacher@active-4.com>

* fix(layers): fix SuRotaryEmbedding

* change arange

* remove logs

* feat: support response_format in chat

* fix: adjust typos

* fix: add trufflehog lint

update commit