Commit Graph

126 Commits

Author SHA1 Message Date
OlivierDehaene 3b56d7669b
feat: add mistral model (#1071) 2023-09-28 09:55:47 +02:00
Merve Noyan 259a230028
Automatic docs for TGI (#1045)
I had to open this PR since I initially worked from my fork, and it
requires a handful of work to trigger a new github action on my fork's
specific branch (couldn't find a way, at least, despite trying all of
them).

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2023-09-27 16:01:38 +02:00
Merve Noyan 36c2868853
Added note on weight-cache-override (#994)
Added note on serving supported models from a different folder without
re-downloading them.

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2023-09-27 11:06:07 +02:00
Nicolas Patry a049864270
Preping 1.1.0 (#1066)
# What does this PR do?

Upgrade all relevant versions and dependencies.

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- 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).
- [ ] 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

 -->
2023-09-27 10:40:18 +02:00
Nicolas Patry c5de7cd886
Add AWQ quantization inference support (#1019) (#1054)
# Add AWQ quantization inference support

Fixes
https://github.com/huggingface/text-generation-inference/issues/781

This PR (partially) adds support for AWQ quantization for inference.
More information on AWQ [here](https://arxiv.org/abs/2306.00978). In
general, AWQ is faster and more accurate than GPTQ, which is currently
supported by TGI.

This PR installs 4-bit GEMM custom CUDA kernels released by AWQ authors
(in `requirements.txt`, just one line change).

Quick way to test this PR would be bring up TGI as follows:

```
text-generation-server download-weights abhinavkulkarni/codellama-CodeLlama-7b-Python-hf-w4-g128-awq

text-generation-launcher \
--huggingface-hub-cache ~/.cache/huggingface/hub/ \
--model-id abhinavkulkarni/codellama-CodeLlama-7b-Python-hf-w4-g128-awq \
--trust-remote-code --port 8080 \
--max-input-length 2048 --max-total-tokens 4096 --max-batch-prefill-tokens 4096 \
--quantize awq
```

Please note:
* This PR was tested with FlashAttention v2 and vLLM.
* This PR adds support for AWQ inference, not quantizing the models.
That needs to be done outside of TGI, instructions

[here](f084f40bd9).
* This PR only adds support for `FlashLlama` models for now.
* Multi-GPU setup has not been tested. 
* No integration tests have been added so far, will add later if
maintainers are interested in this change.
* This PR can be tested on any of the models released

[here](https://huggingface.co/abhinavkulkarni?sort_models=downloads#models).

Please refer to the linked issue for benchmarks for

[abhinavkulkarni/meta-llama-Llama-2-7b-chat-hf-w4-g128-awq](https://huggingface.co/abhinavkulkarni/meta-llama-Llama-2-7b-chat-hf-w4-g128-awq)
vs

[TheBloke/Llama-2-7b-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GPTQ).

Please note, AWQ has released faster (and in case of Llama, fused)
kernels for 4-bit GEMM, currently at the top of the `main` branch at
https://github.com/mit-han-lab/llm-awq, but this PR uses an older commit
that has been tested to work. We can switch to latest commit later on.

## Who can review?

@OlivierDehaene OR @Narsil

---------



# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- 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).
- [ ] 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

 -->

---------

Co-authored-by: Abhinav M Kulkarni <abhinavkulkarni@gmail.com>
Co-authored-by: Abhinav Kulkarni <abhinav@concentric.ai>
2023-09-25 15:31:27 +02:00
Merve Noyan c8a01d7591
Unsupported model serving docs (#906)
Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2023-09-12 15:55:14 +02:00
Merve Noyan e9ae678699
Quantization docs (#911)
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
2023-09-12 15:52:46 +02:00
Merve Noyan 1f69fb9ed4
Tensor Parallelism conceptual guide (#886)
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
2023-09-12 12:11:20 +02:00
Merve Noyan 30a93a0dec
Paged Attention Conceptual Guide (#901) 2023-09-08 14:18:42 +02:00
Merve Noyan af1ed38f39
Safetensors conceptual guide (#905)
IDK what else to add in this guide, I looked for relevant code in TGI
codebase and saw that it's used in quantization as well (maybe I could
add that?)
2023-09-07 16:22:06 +02:00
Omar Sanseviero a9fdfb2464
docs: Remove redundant content from stream guide (#884)
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2023-09-06 18:42:42 +02:00
Merve Noyan f260eb72f9
docs: Flash Attention Conceptual Guide (#892)
PR for conceptual guide on flash attention. I will add more info unless
I'm told otherwise.

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
2023-09-06 15:36:49 +02:00
Julien Bouquillon 3ed4c0f33f
docs: typo in streaming.js (#971)
Looks like an error
2023-09-06 14:57:59 +02:00
Omar Sanseviero 7d8e5fb284
Update version in docs (#957) 2023-08-31 20:00:12 +02:00
Merve Noyan 97444f9367
Added gradio example to docs (#867)
cc @osanseviero

---------

Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
2023-08-23 23:50:12 +02:00
Nicolas Patry 888c029114
Upgrade version number in docs. (#910)
# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- 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).
- [ ] 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

 -->
2023-08-23 13:45:28 +02:00
Omar Sanseviero bfa070611d
Add streaming guide (#858)
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: Merve Noyan <merveenoyan@gmail.com>
2023-08-18 13:27:08 +02:00
Omar Sanseviero d9bceb8e6b
Misc improvements for InferenceClient docs (#852)
List of changes

- No need to specify `model` in `text_generation` if it's already
specified in `InferenceClient`
- I separated the explanation of `stream=True` and `details=True`
- I found the details explanation a bit repetitive (it says two times
what it returns), so removed a sentence
- Add mention of async client
2023-08-16 14:29:54 +02:00
Omar Sanseviero d71237fc8b
Have snippets in Python/JavaScript in quicktour (#809)
![Screenshot from 2023-08-10
14-20-25](https://github.com/huggingface/text-generation-inference/assets/7246357/e16d0d41-be63-4d06-8093-30540df91419)

---------

Co-authored-by: Merve Noyan <merveenoyan@gmail.com>
2023-08-14 13:47:32 +02:00
Nicolas Patry 09eca64227
Version 1.0.1 (#836)
# What does this PR do?

<!--
Congratulations! You've made it this far! You're not quite done yet
though.

Once merged, your PR is going to appear in the release notes with the
title you set, so make sure it's a great title that fully reflects the
extent of your awesome contribution.

Then, please replace this with a description of the change and which
issue is fixed (if applicable). Please also include relevant motivation
and context. List any dependencies (if any) that are required for this
change.

Once you're done, someone will review your PR shortly (see the section
"Who can review?" below to tag some potential reviewers). They may
suggest changes to make the code even better. If no one reviewed your PR
after a week has passed, don't hesitate to post a new comment
@-mentioning the same persons---sometimes notifications get lost.
-->

<!-- 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).
- [ ] 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

 -->
2023-08-14 11:23:11 +02:00
Merve Noyan a2a913eec5
Added streaming for InferenceClient (#821)
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: Omar Sanseviero <osanseviero@gmail.com>
2023-08-11 18:05:19 +03:00
Merve Noyan d0e30771c2
Added ChatUI Screenshot to Docs (#823)
cc @osanseviero
2023-08-11 16:42:43 +02:00
Merve Noyan e58ad6dd66
Added CLI docs (#799)
Added docs for CLI
2023-08-10 15:00:30 +02:00
Omar Sanseviero 7dbaef3f5b
Minor docs style fixes (#806) 2023-08-10 15:32:51 +03:00
Omar Sanseviero 04f7c2d86b
Fix gated docs (#805) 2023-08-10 15:32:07 +03:00
Merve Noyan 647ae7a7d3
Setup for doc-builder and docs for TGI (#740)
I added ToC for docs v1 & started setting up for doc-builder. cc @Narsil
@osanseviero

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: osanseviero <osanseviero@gmail.com>
Co-authored-by: Mishig <mishig.davaadorj@coloradocollege.edu>
2023-08-10 10:24:52 +02:00