Fangzhou AiandClaude Opus 5.5 cc2a6eea1a [ROCm][Perf][DSv4.1] Mono decode on every backbone layer (#61082) ...

Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-13 10:16:50 +08:00

..

__init__.py

Change the name to vLLM (#150)

2023-06-17 03:07:40 -07:00

arg_utils.py

[ROCm][Perf][DSv4.1] Mono decode on every backbone layer (#61082)

2026-10-13 10:16:50 +08:00

async_llm_engine.py

[Docs] Reduce time spent generating API docs (#34255)

2026-02-11 02:56:02 -08:00

llm_engine.py

[Docs] Reduce time spent generating API docs (#34255)

2026-02-11 02:56:02 -08:00

protocol.py

[RL] Release weight-transfer communicators without stopping inference (#61060)

2026-10-11 21:15:14 +08:00