This repository has been archived by the owner on Oct 11, 2024. It is now read-only.
Upstream sync 2024 04 21 #198
Closed
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
Co-authored-by: Woosuk Kwon <[email protected]>
Co-authored-by: Roger Wang <[email protected]>
Co-authored-by: Simon Mo <[email protected]>
…3974) [Bugfix] Fix CustomAllreduce pcie nvlink topology detection (vllm-project#3974) (vllm-project#4159)
…/crash in distributed inference (vllm-project#4079) Co-authored-by: Simon Mo <[email protected]>
Co-authored-by: simon-mo <[email protected]>
Co-authored-by: Zhong Wang <[email protected]>
Co-authored-by: Ubuntu <[email protected]>
Co-authored-by: Harry Mellor <[email protected]>
…roject#4118) Provide an initial support to FP8 computation. This PR is inspired by HuggingFace TGI: huggingface/text-generation-inference#1726 This feature can be enabled with --quantization fp8 or -q fp8 when launching an engine. Algorithm: We still load a model checkpoint in FP16/BF16. After the weights are loaded, Fp8LinearMethod calculates the per-tensor scaling factor of weights and quantizes the weights accordingly. The scaling factor will then be stored for future use. Meanwhile, the per-tensor scaling factor for activations is calculated in every forward pass. Initial Results: Currently tested Mistral-7B on 1xH100. With prompt length ~5 and decoding length 128: BF16: 1.47s FP8: 1.66s I'll try to use larger models and try to find more performance bottleneck. Meanwhile, you're welcome to try this code.
Co-authored-by: Harry Mellor <[email protected]>
…ct#3748) Co-authored-by: Yun Ding <[email protected]> Co-authored-by: Roger Wang <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Upstream sync 2024 04 21 (#198)
SUMMARY:
Merge commits from 7fd3949 to a37d815 into nm-vllm/main
Note that 7fd3949 is NOT included in this merge.