vLLM/vllm/utils at f1fc2107a314ddfdba31348dc134bb861ccd77a1 - vLLM

iHore/vLLM

Fork 0

Files

T

History

502640c3f9 [Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696 )

Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: ElizaWszola <elizaw.9289@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>

2025-10-02 19:35:13 +00:00

__init__.py

[CI/Build] Replace vllm.entrypoints.openai.api_server entrypoint with vllm serve command (#25967 )

2025-10-02 10:04:57 -07:00

deep_gemm.py

[Perf] Fix and reapply move apply w8a8 block fp8 linear to class (#25696 )

2025-10-02 19:35:13 +00:00

flashinfer.py

Support mnnvl all2allv from Flashinfer (#21003 )

2025-09-24 14:38:16 -04:00

gc_utils.py

[Core] GC Debug callback (#24829 )