Commit Graph

40 Commits

Author SHA1 Message Date
drbh cef0553d59
Outlines guided generation (#1539)
This WIP PR starts to add grammar support via outlines, currently this
PR supports very simple regex grammars and does not optimize for
precompiling or caching grammar fsm's.

todo:
- [X] add simple outlines guidance to `NextTokenChooser`
- [X] update protos for grammar
- [X] update generation params API
- [X] constrain simple grammar
- [ ] support parsing more complex grammar into fsm
- [ ] support all outline support grammar types
- [ ] explore optimizations to avoid recompiling grammars

guided request
```bash
curl -s 'http://localhost:3000/generate' \
--header 'Content-Type: application/json' \
--data-raw '{
    "inputs": "make an email for david: \n",
    "parameters": {
        "max_new_tokens": 6,
        "grammar": "[\\w-]+@([\\w-]+\\.)+[\\w-]+"
    }
}' | jq
```
response
```json
{
  "generated_text": "david@example.com"
}
```

unguided request
```bash
curl -s 'http://localhost:3000/generate' \
--header 'Content-Type: application/json' \
--data '{
    "inputs": "make an email for david: \n",
    "parameters": {
        "max_new_tokens": 6
    }
}' | jq
```
response
```json
{
  "generated_text": "    email = 'david"
}
```
2024-02-15 10:28:10 +01:00
OlivierDehaene 09b7c26bbd
feat(server): add frequency penalty (#1541) 2024-02-08 18:41:25 +01:00
Nicolas Patry 069895b985
Fixing top_n_tokens. (#1497)
# What does this PR do?

Superseeds #1459

The fix works as follows.
We updated next_token_chooser to return all logprbs, then
batch_top_n_tokens, now also gets accepted_ids + speculated_length (so
it knows how to interpret the flat logprobs).

We then update the code to return lists ot `Tokens` that it expects.
<!--
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

 -->
2024-01-26 20:13:47 +01:00
OlivierDehaene 50b495f3d8
feat: add more latency metrics in forward (#1346) 2023-12-14 15:59:38 +01:00
OlivierDehaene 72ee382ded chore: formatting 2023-12-11 14:49:52 +01:00
Nicolas Patry 9ecfa16b12
Speculative (#1308) 2023-12-11 12:46:30 +01:00
momonga 7402a355dc
Fix calling cuda() on load_in_8bit (#1153)
This PR addresses an issue where calling `model = model.cuda()` would
throw a ValueError when `quantize` is set to "bitsandbytes".

```
> File "/opt/conda/lib/python3.9/site-packages/text_generation_server/server.py", line 147, in serve_inner
    model = get_model(
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/__init__.py", line 295, in get_model
    return CausalLM(
  File "/opt/conda/lib/python3.9/site-packages/text_generation_server/models/causal_lm.py", line 515, in __init__
    model = model.cuda()
  File "/opt/conda/lib/python3.9/site-packages/transformers/modeling_utils.py", line 1998, in cuda
    raise ValueError(
ValueError: Calling `cuda()` is not supported for `4-bit` or `8-bit` quantized models. Please use the model as it is, since the model has already been set to the correct devices and casted to the correct `dtype`.
```

Co-authored-by: mmnga <mmnga1mmnga@gmail.com>
2023-10-19 10:42:03 +02:00
OlivierDehaene 47954b81e9
feat: format code (#1070) 2023-09-27 12:22:09 +02:00
Nicolas Patry b32e9ce9d5
Remove the stripping of the prefix space (and any other mangling that tokenizers might do). (#1065)
Superseed #1024


# 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: bangoz <ch_xie@pku.edu.cn>
2023-09-27 12:13:45 +02:00
Vincent Brouwers 8672cad2cb
Fix top_n_tokens returning non-log probs for some models (#1023)
# What does this PR do?

I made an embarrassing mistake where I accidentally passed normal
softmax probabilities into `batch_top_tokens` for `CausalLM` and
`Seq2SeqLM`.

<!--
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 -->

## 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.

@Narsil
2023-09-26 16:16:43 +02:00
Wang, Yi eeaa22ab04
enable bfloat16 for cpu (#1034)
if there's no cuda. disable custom kernels

# 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

 -->

Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
2023-09-19 17:19:28 +02:00
Nicolas Patry 211b54ac41
Rebased #617 (#868)
# 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: Vincent Brouwers <vincent.brouwers@ing.com>
2023-08-28 11:43:47 +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
OlivierDehaene 895c5f1562
feat(server): only compute prefill logprobs when asked (#406)
Close #288
2023-06-02 17:12:30 +02:00
OlivierDehaene d69a0633be
fix(server): fix has_position_ids (#395)
Fix #389
2023-06-01 11:41:35 +02:00
OlivierDehaene 62f91f78ac
feat(server): support vectorized warpers in flash causal lm (#317)
Co-authored-by: Joel Lamy-Poirier <joel.lamy-poirier@servicenow.com>
2023-05-26 12:30:27 +02:00
OlivierDehaene 218c9adaa5
feat: decrease IPC proto size (#367)
Closes #307 #308
2023-05-24 19:19:57 +02:00
OlivierDehaene e3e487dc71
feat(server): support trust_remote_code (#363) 2023-05-23 20:40:39 +02:00
OlivierDehaene e9669a4085
feat(server): do not use device_map auto on single GPU (#362) 2023-05-23 19:12:12 +02:00
OlivierDehaene e649bf9a55
feat(server): Support BLOOMChat-176B (#348) (#351)
@njhill, 
temporary workaround to be able to run our CI as secrets are not
available to runners run by external contributors. I will ask around to
see if there is a better way.

Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-05-22 13:36:00 +02:00
OlivierDehaene 5a58226130
fix(server): fix decode token (#334)
Fixes #333

---------

Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
2023-05-16 23:23:27 +02:00
Nicolas Patry 76a48cd365
feat(server): GPTQ quantization (step1) (#277)
Changes only the type from `bool` to `Option<Enum>` pretty much
everywhere.
- Use `Optional[str]` in Python (easier to manage than importing type
everywhere). Except for the cli to get proper validation
- Updated all models to handle gracefully new values. (Error out if
unknown value, or gptq since not implemented).

<!--
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

 -->
2023-05-12 14:46:41 +02:00
OlivierDehaene 745f596c88
feat(server): use float16 (#304) 2023-05-10 15:51:10 +02:00
OlivierDehaene 68e9d6ab33
feat(server): shard token decode (#303) 2023-05-10 15:48:21 +02:00
OlivierDehaene 4096000e34
fix(server): fix typo in tokenizers decode (#269)
closes #268
2023-05-03 10:10:34 +02:00
Nick Hill 34bca0b8d3
fix(server): Small tidy of code from recent changes (#251)
remaining_decode_tokens was calculated twice in Seq2SeqLMBatch.filter()
2023-04-27 09:57:28 +02:00
Nick Hill b4cf832c40
fix(server): fix reshaping of bloom past_key_values in concatenate() (#252)
Introduced in #214 

Fixes #249
2023-04-27 09:51:27 +02:00
OlivierDehaene ebc74d5666
feat(router): use number of tokens in batch as input for dynamic batching (#226)
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
2023-04-24 17:59:00 +02:00
Nick Hill 4a7dd4085a
feat(server): reduce memory requirement (#214) 2023-04-24 14:15:42 +02:00
OlivierDehaene 343437c7b5
feat(router): add device and dtype info (#215) 2023-04-21 15:36:29 +02:00
OlivierDehaene 709d8936f6
feat(router): drop requests when client closes the channel (#202) 2023-04-20 11:07:40 +02:00
OlivierDehaene 5fa8ae041c
feat(server): optimize decode for sane tokenizers (#170) 2023-04-12 12:03:10 +02:00
OlivierDehaene 299217c95c
feat(server): add flash attention llama (#144) 2023-04-11 16:38:22 +02:00
OlivierDehaene 9987960062
feat(router): make router input validation optional (#164) 2023-04-09 20:22:27 +02:00
OlivierDehaene 05e9a796cc
feat(server): flash neoX (#133) 2023-03-24 14:02:14 +01:00
OlivierDehaene b49dbf2d88
fix(server): use server tokenizer as gt (#128) 2023-03-16 12:12:26 +01:00
OlivierDehaene 8ad60b752f
fix(server): add position ids to neox (#126) 2023-03-15 13:12:49 +01:00
OlivierDehaene 941cd42e0c
fix(server): fix index out of range for watermarking (#110) 2023-03-08 18:29:08 +01:00
OlivierDehaene 3fef90d50f
feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00