Yuzhen Zhou 4f3dc1ef5b [ROCm] Use unreg path for custom all-reduce during CUDA graph capture (#19162)

2026-02-22 23:27:31 -08:00

..

device_communicators

[ROCm] Use unreg path for custom all-reduce during CUDA graph capture (#19162)

2026-02-22 23:27:31 -08:00

__init__.py

Roll back to use vllm custom allreduce (#3006)

2025-01-20 04:03:15 -08:00

communication_op.py

Sync distributed package from vllm 0.6.4.post1 (#3010)

2025-01-20 04:57:14 -08:00

naive_distributed.py

vlm: enforce pybase64 for image and str encode/decode (#10700)

2025-10-21 19:05:32 +08:00

parallel_state.py

Fix PCG MoE Error (#17739)

2026-02-19 16:48:06 +08:00

utils.py

Optimize uneven PP layer distribution logic to improve PP performance (#13977)

2025-11-26 22:05:03 +08:00