whx 1b270a64bd [MoE][Multistream] Avoid performing communication in extra stream. (#3582) ...

This PR moves the communication operation of shared experts out of extra
stream because I found that this might cause rtMemcpy related errors
when running shared experts multistream with aclgraph.

Furthermore, I utilize a global variable as extra stream object to avoid
allocating streams for each layer in full-graph mode.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-10-24 10:44:38 +08:00

..

e2e

[MoE][Multistream] Avoid performing communication in extra stream. (#3582)

2025-10-24 10:44:38 +08:00

ut

support cp&dcp (#3260)

2025-10-24 10:32:01 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00