Commit Graph

872 Commits

Author SHA1 Message Date
yuanwu2017
8d84ffabf2
Upgrade to SynapseAI 1.18 (#227)
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: Thanaji Rao Thakkalapelli <tthakkalapelli@habana.ai>
2024-10-31 20:14:44 +01:00
Thanaji Rao Thakkalapelli
7fb4af9a87
updated supported models list table in readme (#241)
* updated supported models list table in readme

* updated read me

* updated read me
2024-10-29 23:28:45 -07:00
Thanaji Rao Thakkalapelli
b126bf4785
Revert pr 235 as flash attention is not really enabled for gemma (#239) 2024-10-23 10:58:57 +02:00
Thanaji Rao Thakkalapelli
c5e3881051
Enables Flash Attention in TGI for gemma models (#235) 2024-10-18 09:20:42 -07:00
Alessandro de Oliveira Faria (A.K.A.CABELO)
9ae5ad5057
requirements name - cabelo@opensuse.org (#237) 2024-10-18 09:20:05 -07:00
Thanaji Rao Thakkalapelli
46b14e6b28
Remove all references to habana_quantization_toolkit for 1.18 (#229) 2024-10-18 10:59:59 +02:00
Thanaji Rao Thakkalapelli
21c13ff3a6
Remove References to torch compile mode in readme (#236) 2024-10-17 14:07:51 -07:00
Sun Choi
8ae5d4c7d6
Ignore EOS for benchmark by using TEXT_GENERATION_SERVER_IGNORE_EOS_TOKEN (#234) 2024-10-16 11:57:36 +02:00
Mandy Li
d07e7f4f62
Merge pull request #233 from huggingface/fix_sysntax
Fix sysntax error in PR 232
2024-10-15 14:33:21 -07:00
Thanaji Rao Thakkalapelli
87a1cee32c
Fix sysntax error in PR 232 2024-10-15 13:23:48 -07:00
Thanaji Rao Thakkalapelli
e06320f64e
Enabling Flash Attention support for falcon model (#232) 2024-10-15 19:50:17 +02:00
Sun Choi
0578bd917d
Fix gpt_bigcode/starcoderbase-3b accuracy issue (#228)
Co-authored-by: Thanaji Rao Thakkalapelli <tthakkalapelli@habana.ai>
2024-10-14 10:01:55 +02:00
Mohit Deopujari
fe8a373831
Enhancements to README (#226) 2024-10-02 12:22:33 +02:00
yuanwu2017
e424752fa3
Enable the AutoGPTQ (#217)
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-09-25 18:55:02 +02:00
regisss
0deebe7012 Update README with Docker image v2.0.5 2024-09-07 17:56:52 +00:00
regisss
bf9865e956
Upgrade to Optimum Habana v1.13.2 (#222) 2024-09-07 19:52:59 +02:00
Thanaji Rao Thakkalapelli
a4f39a1cae
Update README.md with changes related to LLava-next multi card support (#221) 2024-09-07 17:46:21 +02:00
Thanaji Rao Thakkalapelli
ad7c620f0f
Llava-next: Added flash_attention_recompute option (#220) 2024-09-06 22:20:07 +02:00
yuanwu2017
2299b739fe
Only Apply the TP in language_model (#219)
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-09-06 22:19:24 +02:00
Thanaji Rao Thakkalapelli
73d93bdd93
Downgrade sympy to match synapaseAI 1.18 base image (#215) 2024-08-28 17:45:44 +02:00
Thanaji Rao Thakkalapelli
fde061ccf8
Updated docker image version to 2.0.4 (#212)
Co-authored-by: Thanaji Thakkalapelli <tthakkalapelli@tthakkalapelli-vm-u22.habana-labs.com>
2024-08-27 10:14:27 +02:00
yuanwu2017
2985503900
llava-next Fp8 (#209)
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: Thanaji Rao Thakkalapelli <tthakkalapelli@habana.ai>
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
2024-08-26 16:53:08 +02:00
Wang, Chang
55d60a103c
Add qwen2 fp8 support (#210)
Signed-off-by: changwang <changwang@habana.ai>
Co-authored-by: changwang <changwang@habana.ai>
2024-08-26 11:02:58 +02:00
Thanaji Rao Thakkalapelli
e33db1877c
Updated Readme to use flash attention for llama (#200) 2024-08-26 11:01:11 +02:00
Vidya Galli
c925bd2872
Undo disable of hpu graphs for starcoder (#201) 2024-08-26 10:58:01 +02:00
Thanaji Rao Thakkalapelli
0c3239e710
Enable quantization with INC (#203) 2024-08-26 10:55:37 +02:00
Sun Choi
ea48ae169a
Make prefill time of static benchmark correct (#214) 2024-08-26 10:51:28 +02:00
yuanwu2017
a8cead1f92
Upgrade SynapseAI version to 1.17.0 (#208)
Signed-off-by: yuanwu <yuan.wu@intel.com>
Co-authored-by: Thanaji Rao Thakkalapelli <tthakkalapelli@habana.ai>
Co-authored-by: regisss <15324346+regisss@users.noreply.github.com>
2024-08-26 10:49:29 +02:00
yuanwu2017
369e499a66
Simplify the warmup process (#173)
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-08-15 12:04:14 +02:00
Sun Choi
e3f0f85b70
Pad token handling for Llama3.1 (#199) 2024-08-13 00:00:41 +02:00
regisss
c09f5bc930
Merge pull request #187 from yuanwu2017/v2.0.4 2024-08-12 23:59:03 +02:00
Abhilash Majumder
d403575c43
Make bf16 default for hpu, fix script (#205) 2024-08-11 10:48:35 +02:00
Sun Choi
cf2ff5a1dd
Revert PR#178 (#191) 2024-08-11 09:29:30 +02:00
regisss
a41e974c3b
Merge branch 'habana-main' into v2.0.4 2024-08-10 12:54:00 +02:00
geoffrey papilion
e36a9c57f0
Code expects newer huggingface_hub versions, tested and this resolves issues with streaming response format (#190)
Co-authored-by: Geoffrey Papilion <gpapilion@ebay.com>
2024-08-08 13:07:27 +02:00
Jacek Czaja
256a97231b
Removed redundant and crash causing regions to be a subject to Torch compile (#194)
Co-authored-by: Jacek Czaja <jczaja@habana.ai>
2024-08-08 13:06:20 +02:00
Vidya Galli
4dc67e4ef3
Version check, doc fixes (#182) 2024-08-07 22:09:51 +02:00
Abhilash Majumder
9b71343328
Integrate flash attention for starcoder2 tgi through habana and some fixes, enabling (#198) 2024-08-07 22:06:05 +02:00
yuanwu
d34ffc4fe9 Refile the hpu warmup
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-08-02 04:36:59 +00:00
yuanwu
05c13c89de Remove useless modification
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-07-30 10:05:38 +00:00
yuanwu
3f0f0e0825 Add the habana profiler
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-07-30 03:53:46 +00:00
yuanwu
db0b6567e1 Remove log
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-07-29 22:02:42 +00:00
yuanwu
588a014551 Enable llava-next
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-07-29 21:55:31 +00:00
yuanwu2017
d3155d6f41
Merge branch 'habana-main' into v2.0.4 2024-07-17 13:45:15 +08:00
yuanwu
b34edc2ee9 Upgrade to 2.0.4
Signed-off-by: yuanwu <yuan.wu@intel.com>
2024-07-17 05:36:58 +00:00
Nicolas Patry
179336888e Modifing the version number. 2024-07-17 05:36:58 +00:00
Nicolas Patry
42b0847a80 Fixing codellama loads by using purely AutoTokenizer. (#1947)
- The need for the slow tokenizer default stems from back
  when llama 1 was introduced and all the flags where not
  supported in `tokenizers`.

- Fixes #1891

# 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

 -->
2024-07-17 05:36:58 +00:00
Nicolas Patry
075092315e Improving the logging system. (#1938)
- Added a debug log for speculated ids (helps seeing in logs quality of
  a speculator).
- Remove newlines from child process logs when re-emitting in non JSON
  mode.
- Made standard level be closer to what's expected (only our binaries
  level).
- Propagate that level correctly to the shard (was forced into INFO).

# 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

 -->
2024-07-17 05:36:58 +00:00
Thomas Schillaci
4239e4d327 Add completion route to client and add stop parameter where it's missing (#1869)
# What does this PR do?

- Add the stop parameter to the completion route
- Add the completion method to the python client
- Add the stop parameter to the python client's chat method

## 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.

@Narsil

---------

Co-authored-by: Thomas SCHILLACI <tschilla@px101.prod.exalead.com>
Co-authored-by: Thomas Schillaci <thomas.schillaci@3ds.com>
2024-07-17 05:36:58 +00:00
Nicolas Patry
7cf21294d1 Fixing some legacy behavior (big swapout of serverless on legacy stuff). (#1937)
# 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: Daniël de Kok <me@github.danieldk.eu>
2024-07-17 05:36:58 +00:00