feat: eetq gemv optimization when batch_size <= 4 #1502
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Good job! |
helena-intel
pushed a commit
to helena-intel/text-generation-inference-hf
that referenced
this pull request
Feb 1, 2024
# 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 --> Add TensorRT-LLM weight-only GEMV kernel support. We extract GEMV kernel from [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/tree/main/cpp/tensorrt_llm/kernels/weightOnlyBatchedGemv) to accelerate the decode speed of EETQ when batch_size is smaller or equal to 4. - Features 1. There is almost no loss of quantization accuracy. 2. The speed of decoding is 13% - 27% faster than original EETQ which utilizes GEMM kernel. - Test Below is our test on 3090. Environment: torch=2.0.1, cuda=11.8, nvidia driver: 525.78.01 prompt=1024, max_new_tokens=50   ## 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 -->
kdamaszk
pushed a commit
to kdamaszk/tgi-gaudi
that referenced
this pull request
Apr 29, 2024
# 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 --> Add TensorRT-LLM weight-only GEMV kernel support. We extract GEMV kernel from [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/tree/main/cpp/tensorrt_llm/kernels/weightOnlyBatchedGemv) to accelerate the decode speed of EETQ when batch_size is smaller or equal to 4. - Features 1. There is almost no loss of quantization accuracy. 2. The speed of decoding is 13% - 27% faster than original EETQ which utilizes GEMM kernel. - Test Below is our test on 3090. Environment: torch=2.0.1, cuda=11.8, nvidia driver: 525.78.01 prompt=1024, max_new_tokens=50   ## 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 -->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Add TensorRT-LLM weight-only GEMV kernel support. We extract GEMV kernel from TensorRT-LLM to accelerate the decode speed of EETQ when batch_size is smaller or equal to 4.
Below is our test on 3090. Environment: torch=2.0.1, cuda=11.8, nvidia driver: 525.78.01
prompt=1024, max_new_tokens=50
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
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.