Cheng Wan 453511acc7 Save memory for expert model parallel (#9957)

2025-09-04 13:31:47 -07:00

..

device_communicators

Add fp4 quantize before all-gather for Flashinfer cutlass MoE DP (max throughput) (#7667)

2025-08-15 22:08:11 -07:00

__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

Overlapped weight offload (#8034)

2025-08-23 02:06:46 -07:00

parallel_state.py

Save memory for expert model parallel (#9957)

2025-09-04 13:31:47 -07:00

utils.py

Use monotonic clock for interval measurement (#6211)

2025-05-17 16:49:18 -07:00