Woosuk KwonandCodex 9a70c233cd [Perf][DSV4.1] Fuse TP all-reduce with mHC input preparation (#57643) ...

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Codex <noreply@openai.com>

2026-09-20 20:28:06 -07:00

..

ops

[Perf][DSV4.1] Optimize MegaMoE staging and NVFP4 cache gathers (#57604)

2026-09-18 12:57:19 -07:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00

dspark.py

[DSv4.1] Integrate Mega-Gate from DeepGEMM (#56266)

2026-09-17 12:06:36 -07:00

fi_moe.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

flashinfer_sparse.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

flashmla.py

[New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)

2026-09-02 11:09:09 -07:00

model.py

[Perf][DSV4.1] Fuse TP all-reduce with mHC input preparation (#57643)

2026-09-20 20:28:06 -07:00

mtp.py

[DSv4.1] Integrate Mega-Gate from DeepGEMM (#56266)

2026-09-17 12:06:36 -07:00

vl_model.py

[Model][ROCm] Enable DeepSeek V4 Vision (#55107)

2026-09-11 09:17:30 -07:00