[Kernel] Support Fp8 Checkpoints for Mixtral (Dynamic + Static) #4436
Conversation
This file contains hidden or 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
re-added opt change, will fix in another PR
Co-authored-by: Michael Goin <[email protected]>
Co-authored-by: Michael Goin <[email protected]>
robertgshaw2-redhat
changed the title
robertgshaw2-redhat
changed the title
comaniac
approved these changes
May 1, 2024
| if self.use_fp8: | ||
| # WEIGHT_SCALE (for fp8) | ||
| self.ws_scale = nn.Parameter(torch.ones(self.num_total_experts, | ||
| device="cuda", |
Collaborator
There was a problem hiding this comment.
Remove all device="cuda" in this or the next PR.
Collaborator
Author
pcmoritz
pushed a commit
that referenced
this pull request
May 4, 2024
… Dynamic/Static Activations) (#4527) Follow on to #4332 to enable FP8 checkpoint loading for Mixtral and supersedes #4436. This PR enables the following checkpoint loading features for Mixtral: Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model Supports static or dynamic activation quantization with static weight quantization (all per tensor) Supports different scales for each expert weight Supports Fp8 in QKV layer Notes: The Expert Gate/Router always runs at half / full precision for now. If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.
robertgshaw2-redhat
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
May 6, 2024
… Dynamic/Static Activations) (vllm-project#4527) Follow on to vllm-project#4332 to enable FP8 checkpoint loading for Mixtral and supersedes vllm-project#4436. This PR enables the following checkpoint loading features for Mixtral: Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model Supports static or dynamic activation quantization with static weight quantization (all per tensor) Supports different scales for each expert weight Supports Fp8 in QKV layer Notes: The Expert Gate/Router always runs at half / full precision for now. If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.
z103cb
pushed a commit
to z103cb/opendatahub_vllm
that referenced
this pull request
May 7, 2024
… Dynamic/Static Activations) (vllm-project#4527) Follow on to vllm-project#4332 to enable FP8 checkpoint loading for Mixtral and supersedes vllm-project#4436. This PR enables the following checkpoint loading features for Mixtral: Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model Supports static or dynamic activation quantization with static weight quantization (all per tensor) Supports different scales for each expert weight Supports Fp8 in QKV layer Notes: The Expert Gate/Router always runs at half / full precision for now. If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.
dtrifiro
pushed a commit
to opendatahub-io/vllm
that referenced
this pull request
May 7, 2024
… Dynamic/Static Activations) (vllm-project#4527) Follow on to vllm-project#4332 to enable FP8 checkpoint loading for Mixtral and supersedes vllm-project#4436. This PR enables the following checkpoint loading features for Mixtral: Supports loading fp8 checkpoints for Mixtral, such as this "nm-testing/Mixtral-8x7B-Instruct-v0.1-FP8" test model Supports static or dynamic activation quantization with static weight quantization (all per tensor) Supports different scales for each expert weight Supports Fp8 in QKV layer Notes: The Expert Gate/Router always runs at half / full precision for now. If there are different weight scales between QKV layer (for separate QKV weights), they are re-quantized using layer.weight_scale.max() so we can have a single gemm for performance.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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.
Follow on to #4332 (should wait until 4332 is merged)
This PR does a few things:
Note: performance of QKV layer (for separate QKV weights) requires optimization via Cutlass kernels
Next Steps:
TODO: quick test with loading fp16 models (note for rs: act_scales.max() might be wrong in that case)
PR Checklist (Click to Expand)
Thank you for your contribution to vLLM! Before submitting the pull request, please ensure the PR meets the following criteria. This helps vLLM maintain the code quality and improve the efficiency of the review process.
PR Title and Classification
Only specific types of PRs will be reviewed. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:
[Bugfix]for bug fixes.[CI/Build]for build or continuous integration improvements.[Doc]for documentation fixes and improvements.[Model]for adding a new model or improving an existing model. Model name should appear in the title.[Frontend]For changes on the vLLM frontend (e.g., OpenAI API server,LLMclass, etc.)[Kernel]for changes affecting CUDA kernels or other compute kernels.[Core]for changes in the core vLLM logic (e.g.,LLMEngine,AsyncLLMEngine,Scheduler, etc.)[Hardware][Vendor]for hardware-specific changes. Vendor name should appear in the prefix (e.g.,[Hardware][AMD]).[Misc]for PRs that do not fit the above categories. Please use this sparingly.Note: If the PR spans more than one category, please include all relevant prefixes.
Code Quality
The PR need to meet the following code quality standards:
format.shto format your code.docs/source/if the PR modifies the user-facing behaviors of vLLM. It helps vLLM user understand and utilize the new features or changes.Notes for Large Changes
Please keep the changes as concise as possible. For major architectural changes (>500 LOC excluding kernel/data/config/test), we would expect a GitHub issue (RFC) discussing the technical design and justification. Otherwise, we will tag it with
rfc-requiredand might not go through the PR.What to Expect for the Reviews
The goal of the vLLM team is to be a transparent reviewing machine. We would like to make the review process transparent and efficient and make sure no contributor feel confused or frustrated. However, the vLLM team is small, so we need to prioritize some PRs over others. Here is what you can expect from the review process:
action-requiredlabel on the PR if there are changes required. The contributor should address the comments and ping the reviewer to re-review the PR.Thank You
Finally, thank you for taking the time to read these guidelines and for your interest in contributing to vLLM. Your contributions make vLLM a great tool for everyone!