frozenleaves/vllm-ascend
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm-ascend.git synced 2025-10-20 13:43:53 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
vllm-ascend/vllm_ascend/eplb
History
yechao237 4750d45d86 [BugFix]Support redundant experts in EPLB (#3473) 
This PR adds support for redundant experts in the EPLB. 

Key points: 
- Use global_num_experts = num_experts + num_redundant_experts
consistently.
- Backward compatible when num_redundant_experts=0. 

Tested 
On a 16-rank setup (W8A8) with static EPLB and expert_map_path,
verifying router logits shape and successful requests.

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

Signed-off-by: yechao237 <yechao20180411@gmail.com>
2025-10-18 00:09:16 +08:00
..
adaptor
[BugFix]Fix eplb problems when using dynamic eplb. (#3364)
2025-10-11 14:04:02 +08:00
core
[BugFix]Support redundant experts in EPLB (#3473)
2025-10-18 00:09:16 +08:00
__init__.py
Dynamic Expert Load Balance with Zero-like-overhead (#2956)
2025-09-17 10:36:43 +08:00
eplb_updator.py
[EPLB]Record expert map without dynamic eplb. (#3409)
2025-10-15 14:21:15 +08:00
utils.py
Dynamic Expert Load Balance with Zero-like-overhead (#2956)
2025-09-17 10:36:43 +08:00