GitLab

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: Ubuntu <ubuntu@ip-172-31-13-147.ec2.internal>

Co-authored-by: SangBin Cho <sangcho@sangcho-LT93GQWG9C.local>

Co-authored-by: Simon Mo <simon.mo@hey.com>

Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

[Core][Model] Use torch.compile to accelerate layernorm in commandr (#3985)

[WIP][Core][Refactor] move vllm/model_executor/parallel_utils into vllm/distributed and vllm/device_communicators (#3950)

Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>

Co-authored-by: roy <jasonailu87@gmail.com>

Co-authored-by: Egor Tolmachev <t333ga@gmail.com>

Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu>
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com>
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com>
Co-authored-by: guofangze <guofangze@kuaishou.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

[Core][Test] move local_rank to the last arg with default value to keep api compatible (#3711)