- 09 Mar, 2026 1 commit
-
-
yangshj1 authored
-
- 05 Mar, 2026 2 commits
- 27 Feb, 2026 1 commit
-
-
zhuwenwen authored
fix: zero overhead KERNEL VMFault See merge request dcutoolkit/deeplearing/vllm!446
-
- 26 Feb, 2026 1 commit
-
-
jujl1 authored
-
- 25 Feb, 2026 3 commits
- 12 Feb, 2026 2 commits
- 11 Feb, 2026 3 commits
- 09 Feb, 2026 8 commits
- 08 Feb, 2026 1 commit
-
-
王敏 authored
-
- 07 Feb, 2026 1 commit
-
-
zhuwenwen authored
去掉DTBmm的一个冗余条件 See merge request dcutoolkit/deeplearing/vllm!416
-
- 06 Feb, 2026 6 commits
-
-
wujl5 authored
-
zhuwenwen authored
perf: mla后面的DTbmm融合 See merge request dcutoolkit/deeplearing/vllm!415
-
wujl5 authored
-
zhuwenwen authored
feat:w4a8Linear调用apply_int8_linear,以支持blaslt See merge request dcutoolkit/deeplearing/vllm!413
-
jujl1 authored
-
zhuwenwen authored
V0.9.2 dev du connector See merge request dcutoolkit/deeplearing/vllm!409
-
- 05 Feb, 2026 6 commits
-
-
zhuwenwen authored
fix: 修复重复判断逻辑 See merge request dcutoolkit/deeplearing/vllm!406
-
jujl1 authored
-
xuxz authored
[P/D] add new connector as the self-developed du_swift_connector See merge request dcutoolkit/deeplearing/vllm!405
-
xuxz authored
# Conflicts: # vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py
-
zhuwenwen authored
feat: Support shared experts fusion. See merge request dcutoolkit/deeplearing/vllm!404
-
wanglong3 authored
feat: support moe sum when topk==9 bugfix: Fix mtp model load error when eable shared experts fusion.
-
- 04 Feb, 2026 1 commit
-
-
zhuwenwen authored
fix: 修复pp资源抢占bug See merge request dcutoolkit/deeplearing/vllm!402
-
- 03 Feb, 2026 1 commit
-
-
jujl1 authored
-
- 02 Feb, 2026 2 commits
- 29 Jan, 2026 1 commit
-
-
zhuwenwen authored
-