Commit Graph

225 Commits

Author SHA1 Message Date
Nicolas Patry d3d8f1bd6b
Typo fix. (#746)
# 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

 -->
2023-07-31 18:57:29 +02:00
Nicolas Patry 15fc64668f
fix(server): Failing quantize config after local read. (#743)
# 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

 -->
2023-07-31 17:51:26 +02:00
Ikko Eltociear Ashimine 2a13f1a046
chore: fix typo in mpt_modeling.py (#737)
# What does this PR do?
Fixed typo.
<!--
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 -->

implemetation -> implementation


## Before submitting
- [x] 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

 -->
2023-07-31 15:43:44 +02:00
Nicolas Patry 932bdd93ff
Adding Rope scaling. (#741)
# What does this PR do?


- Adds Rope NTK scaling.

Done because
https://github.com/huggingface/text-generation-inference/pull/529 was
closed
Took some code from
https://github.com/huggingface/transformers/pull/24653

- `--rope-scaling` and `--rope-factor` are added separately. I
considered having a single one and parsing something line ("linear:4.0"
, or "dynamic") but decided against
it because it would push more parsing+validation a bit everywhere (both
in the launcher and the server).


Fixes #512




<!--
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

 -->
2023-07-31 15:38:47 +02:00
Jae-Won Chung b9633c46d0
Fix typing in `Model.generate_token` (#733)
## What does this PR do?

This PR fixes a minor type annotation issue in the signature of
`Model.generate_token`.

All existing overrides of `Model.generate_token` return
`Tuple[List[Generation], Optional[B]]`:

3ef5ffbc64/server/text_generation_server/models/causal_lm.py (L535-L537)

3ef5ffbc64/server/text_generation_server/models/flash_causal_lm.py (L802-L804)

3ef5ffbc64/server/text_generation_server/models/seq2seq_lm.py (L589-L591)

I suspect that back in 017a2a8c when `GeneratedText` and `Generation`
were separated, the function signature was not updated.

## 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?

CC @OlivierDehaene
2023-07-31 14:35:14 +02:00
Nicolas Patry 92bb56b0c1
Local gptq support. (#738)
# What does this PR do?

Redoes #719

<!--
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

 -->
2023-07-31 10:32:52 +02:00
OlivierDehaene 3ef5ffbc64
v1.0.0 (#727) 2023-07-28 17:43:46 +02:00
OlivierDehaene afd04dc71e
feat(server): update vllm version (#723) 2023-07-28 15:36:38 +02:00
OlivierDehaene 9f18f4c006
v0.9.4 (#713) 2023-07-27 19:25:15 +02:00
OlivierDehaene ab96b9aec3
feat(server): support new falcon config (#712) 2023-07-27 18:38:57 +02:00
OlivierDehaene 2efd46ef95 fix(server): fix missing datasets in quantize 2023-07-27 14:50:45 +02:00
OlivierDehaene 8bd0adb135
fix(server): fix quantization python requirements (#708) 2023-07-27 12:28:10 +02:00
Nicolas Patry a0d55358d2
feat(server): Using `quantize_config.json` instead of GPTQ_BITS env variables. (#671)
- Current PR is not great because we're side stepping the
  `Weights.__init__` but Weights shouldn't requires anything related
  to the config or the model_id as it aims to be a simple Wrapper
  over multi file loading.
- Ideal solution would be to use something like Rust enum
  ```
  enum Quantize{
    Bitandbytes(Bitsandbytes),
    GPTQ(bits: usize, groupsize: usize)
  ```
  And passing that around during load. Unfortunately we don't
  have access to this, so for now, side-stepping seems easier.

- Re-enabling groupsize<0 with exllama (confirmed it works.)

Helps #601 

In next steps we should make sure our quantization script uses that
format and make it standard.


# 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

 -->
2023-07-25 13:00:27 +02:00
OlivierDehaene 37df6df38e
fix(server): fix exllama buffers (#689)
Close #683
2023-07-24 14:25:43 +02:00
OlivierDehaene 73a4d65d26
feat: add cuda memory fraction (#659)
Close #673
2023-07-24 11:43:58 +02:00
Yang, Bo 15b3e9ffb0
Directly load GPTBigCode to specified device (#618)
This PR directly load GPTBigCode to specified device, avoiding moving
model between devices.

# What does this PR do?
This PR directly load GPTBigCode to specified device, avoiding moving
model between devices.


## 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.


@OlivierDehaene OR @Narsil
2023-07-21 11:27:31 +02:00
Nicolas Patry d5b5bc750f
feat(server): Add exllama GPTQ CUDA kernel support #553 (#666)
Just trying to get the integration tests to pass.


# 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: Felix Marty <9808326+fxmarty@users.noreply.github.com>
2023-07-21 10:59:00 +02:00
OlivierDehaene bf94df3c71
fix(server): use mem_get_info to get kv cache size (#664)
Close
https://github.com/huggingface/text-generation-inference/issues/649
Close
https://github.com/huggingface/text-generation-inference/issues/651
Close
https://github.com/huggingface/text-generation-inference/issues/653
Close #636
2023-07-20 17:23:49 +02:00
Nicolas Patry 08b8eec1d7
fix(server): Fixing non parameters in quantize script `bigcode/starcoder` was an example. (#661) 2023-07-20 16:04:15 +02:00
fxmarty 362883f259
fix(server): llama v2 GPTQ (#648)
As per title & reported
https://github.com/huggingface/text-generation-inference/issues/601#issuecomment-1641435956
https://huggingface.co/TheBloke/Llama-2-70B-chat-GPTQ/discussions/5

Test it:

```
GPTQ_BITS=4 GPTQ_GROUPSIZE=1 text-generation-launcher --model-id TheBloke/Llama-2-70B-chat-GPTQ --port 8080 --num-shard 4 --quantize gptq
```
&
```
curl 127.0.0.1:8080/generate \
    -X POST \
    -d '{"inputs":"hey llama","parameters":{"max_new_tokens":256}}' \
    -H 'Content-Type: application/json'
```
2023-07-20 15:02:54 +02:00
cdawg 214c06f510
Add trust_remote_code to quantize script (#647)
# 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 a bug appeared with MR #587 fixing issue #552.
See the discussion in #552.

With MR #587 the trust_remote_code variable is not passed to
AutoModelForCausalLM, but is found in the function signature. This
prevents models like falcon to be quantized, because trust_remote_code
is required. This MR fixes the 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?
- [X] 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.
@Narsil
<!-- Your PR will be replied to more quickly if you can figure out the
right person to tag with @

 -->
2023-07-20 13:53:08 +02:00
OlivierDehaene fe80f5360c
feat(server): auto max_batch_total_tokens for flash att models (#630) 2023-07-19 09:31:25 +02:00
OlivierDehaene 5e6ddfd6a4
fix(server): fix llamav2 config (#635) 2023-07-18 18:49:42 +02:00
OlivierDehaene cf83f9b66f
v0.9.3 (#634) 2023-07-18 18:11:20 +02:00
Nicolas Patry 211b211ec0
feat(server): add support for llamav2 (#633) 2023-07-18 18:09:53 +02:00
OlivierDehaene 3b71c38558
feat(server): flash attention v2 (#624) 2023-07-18 16:21:18 +02:00
Nicolas Patry 4d38a1c4ad
feat(server): Reworking the quantization script so it's still universal (not llama specific) (#587)
but should work on more configurations (no need for 2 GPUs, less RAM
usage).


# What does this PR do?

Reworking the quantization script so it's still universal (not llama
specific)

but should work on more configurations (no need for 2 GPUs, less RAM
usage).

Still need to investigate the potential differences in quantization
results.


<!--
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

 -->
2023-07-18 12:19:05 +02:00
OlivierDehaene a2cf1bdb2f fix(server): empty_cache when stopped 2023-07-15 13:58:19 +02:00
OlivierDehaene c58a0c185b
v0.9.2 (#616) 2023-07-14 16:31:48 +02:00
OlivierDehaene 5b9de4a1d3
fix(server): blacklist local files (#609)
Close #589 #602
2023-07-13 21:54:55 +02:00
ssmi153 3628559516
GPTQ Env vars: catch correct type of error (#596)
# What does this PR do?

When passing in environment variables like gptq_bits, we still get
errors thrown from TGI because the try/catch block is catching the wrong
type of error. This PR aims to fix that.

@Narsil - let me know if this is how you want this formatted. My Python
is a little shaky, so I hope this syntax is correct.
2023-07-12 19:57:46 +02:00
OlivierDehaene f2f0289fb9 feat(server): empty cache on errors 2023-07-12 17:06:19 +02:00
Nicolas Patry 67347950b7
feat(server): Implements sharding for non divisible `vocab_size`. (#583)
- The code is relatively easy (just disable the checks on Embedding and
Head)

This cannot be done in the same easy fashion for hidden_dim/head_dim.
It's relatively easy on some models (classic MHA) but it would make the
other
models (MQA) much more complex, and GPTQ quantization another quite
hairy piece
of code.
2023-07-12 16:43:31 +02:00
ssmi153 2c4bf88268
fix(server): Bug fixes for GPTQ_BITS environment variable passthrough (#590)
# What does this PR do?

This fixes a typo and extends the GPTP_BITS environment variables
through to the second method which requires the same logic. Please let
me know if there's anything I've misunderstood in this change.

Thanks @Narsil for the original fix.
2023-07-12 14:17:35 +02:00
Adam Kowalski 7f9072228a
fix(server): Adding logger import to t5_modeling.py (#585)
Logger is referenced during the apex importing but is not imported,
causing a NameError
2023-07-12 10:40:32 +02:00
Nicolas Patry db4efbf4bc
fix(server): T5 weights names. (#582)
Fixes #541
2023-07-12 10:01:42 +02:00
Nicolas Patry 5bd2ab6583
feat(server): Support for env value for GPTQ_BITS and GPTQ_GROUPSIZE. (#580)
# What does this PR do?

Some models are already converted, and do not have those values in the
file, this enables users to use them with less friction.

Went for pure env based because adding flags would end up (imo) very
tedious to maintain. There's a lot of sanitation to do: those flags
would be errors if not used in conjuction with `--quantize gptq`.
Then the flags need to exist in the launcher and the server passing them
all throughout all function calls.

This PR is intended as an easy escape hatch, not the defacto method to
use gptq in TGI.

Fixes #500
2023-07-12 10:00:02 +02:00
Nicolas Patry f0181436f4
fix(server): Fixing RW code (it's remote code so the Arch checking doesn't work to see which weights to keep). (#579)
Fixes #555
2023-07-12 09:51:34 +02:00
OlivierDehaene b4024edd45
feat: better errors for warmup and TP (#575)
Close #571
2023-07-10 14:47:15 +02:00
Nicolas Patry e943a294bc
fix(server): harden the weights choice to save on disk. (#561)
- Look at `transformers` base class to check for
  `_key_to_ignore_on_load_missing` or `_tied_weights` which are the
  standard attributes to select the keys to NOT save on disk (since they
  are ignored)

- Modified safetensors code (to be reflected in safetensors even if it's
  an internal function).
  
- Will not work for trust_remote_code=True repos (like santacoder).

Should help with :
https://github.com/huggingface/text-generation-inference/issues/555
and : https://github.com/huggingface/text-generation-inference/pull/501
and https://github.com/huggingface/text-generation-inference/issues/556
and
https://github.com/huggingface/text-generation-inference/issues/482#issuecomment-1623713593
2023-07-07 14:50:12 +02:00
OlivierDehaene 31b36cca21
v0.9.1 (#558) 2023-07-06 16:05:42 +02:00
OlivierDehaene c4bb5264ac
fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
OlivierDehaene 31e2253ae7
feat(server): use latest flash attention commit (#543)
@njhill FYI
2023-07-04 20:23:55 +02:00
Nick Hill e4b26aa10b
fix(server): avoid errors for very small top_p values (#544)
See https://github.com/huggingface/transformers/pull/24111

I didn't add validation to the `__init__` method since it's not done for
other values/warpers.
2023-07-04 20:11:33 +02:00
Antoni Baum 2a101207d4
fix(server): Handle loading from local files for MPT (#534)
This PR allows the MPT model to be loaded from local files. Without this
change, an exception will be thrown by `hf_hub_download` function if
`model_id` is a local path.
2023-07-04 18:37:25 +02:00
Antoni Baum 8405581fcd
fix: Update server/Makefile to include Makefile-vllm (#520)
# What does this PR do?

For consistency and ease of use (you can just run `make` to install vllm
without any extra steps).

<!--
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

 -->
2023-07-04 09:39:25 +02:00
Nicolas Patry 1da07e85aa
feat(server): Add Non flash MPT. (#514)
# What does this PR do?


This adds a non flash version of MPT.
Flash is harder because we need to create a bias ready cuda kernel of
flash attention.

Fixes
https://github.com/huggingface/text-generation-inference/issues/361
Fixes
https://github.com/huggingface/text-generation-inference/issues/491
Fixes
https://github.com/huggingface/text-generation-inference/issues/290
2023-07-03 13:01:46 +02:00
OlivierDehaene e28a809004
v0.9.0 (#525) 2023-07-01 19:25:41 +02:00
Nicolas Patry ecf6dc3a5a
feat: Add the option to force another dtype than `f16`. (#513) 2023-06-30 20:30:09 +02:00
OlivierDehaene e74bd41e0f
feat(server): add paged attention to flash models (#516)
Closes #478
2023-06-30 19:09:59 +02:00