vllm/v1/worker/gpu_model_runner.py · dcb5624aa2460d62ca09304a053a98ec633b0f79 · OpenDAS / vllm_cscc

[Feature] support sequence parallelism using compilation pass (#16155) · 690fe019

cascade authored Apr 27, 2025


Signed-off-by: cascade812 <cascade812@outlook.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

690fe019

gpu_model_runner.py 81.1 KB

Replace gpu_model_runner.py