hf_text-generation-inference/server
Daniël de Kok d14eaacaca
Support GPTQ models with column-packed up/gate tensor (#2006)
# What does this PR do?

The GPTQ code path for column-packed packed tensors assumed that this is
always a QKV matrix. However, models (e.g. Phi-3) can also have
column-packed MLP up/gate matrices.

<!-- Remove if not applicable -->

Fixes # (issue)


## Before submitting
- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [x] 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?

Anyone in the community is free to review the PR once the tests have
passed. Feel free to tag
members/contributors who may be interested in your PR.

<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @


@OlivierDehaene OR @Narsil

 -->
2024-06-04 19:37:49 +02:00
..
custom_kernels chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
exllama_kernels MI300 compatibility (#1764) 2024-05-17 15:30:47 +02:00
exllamav2_kernels chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
tests Refactor layers. (#1866) 2024-05-13 12:44:30 +02:00
text_generation_server Support GPTQ models with column-packed up/gate tensor (#2006) 2024-06-04 19:37:49 +02:00
.gitignore Impl simple mamba model (#1480) 2024-02-08 10:19:45 +01:00
Makefile feat: add SchedulerV3 (#1996) 2024-06-04 15:56:56 +02:00
Makefile-awq chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
Makefile-eetq Upgrade EETQ (Fixes the cuda graphs). (#1729) 2024-04-12 08:15:28 +02:00
Makefile-flash-att chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
Makefile-flash-att-v2 Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986) 2024-05-31 17:57:01 +02:00
Makefile-selective-scan chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
Makefile-vllm MI300 compatibility (#1764) 2024-05-17 15:30:47 +02:00
README.md chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
poetry.lock Fix seeded output. (#1949) 2024-05-24 15:36:13 +02:00
pyproject.toml Fix seeded output. (#1949) 2024-05-24 15:36:13 +02:00
requirements_cuda.txt Fix seeded output. (#1949) 2024-05-24 15:36:13 +02:00
requirements_intel.txt reable xpu, broken by gptq and setuptool upgrade (#1988) 2024-06-03 16:07:50 +02:00
requirements_rocm.txt Fix seeded output. (#1949) 2024-05-24 15:36:13 +02:00

README.md

Text Generation Inference Python gRPC Server

A Python gRPC server for Text Generation Inference

Install

make install

Run

make run-dev