"vllm/vscode:/vscode.git/clone" did not exist on "986537f1c3c8288635b1f00944409489ab1cf21b"
- 26 Sep, 2025 9 commits
-
-
zhuwenwen authored
feat: moe_align_block_size 更新lightop 接口,加入对ep的支持 See merge request dcutoolkit/deeplearing/vllm!216
-
jujl1 authored
-
-
zhuwenwen authored
-
zhuwenwen authored
add PD P do pp See merge request dcutoolkit/deeplearing/vllm!215
-
xiabo authored
-
zhuwenwen authored
[fix] pp+mtp bs 1 correctness See merge request dcutoolkit/deeplearing/vllm!214
-
zhuwenwen authored
add shared_output and routed_scaling_factor of CompressedTensorsW8A8Int8MoEMethod
-
lizhigong authored
-
- 25 Sep, 2025 4 commits
- 24 Sep, 2025 4 commits
- 23 Sep, 2025 6 commits
- 22 Sep, 2025 2 commits
- 17 Sep, 2025 2 commits
- 16 Sep, 2025 3 commits
- 15 Sep, 2025 2 commits
- 14 Sep, 2025 8 commits
-
-
zhuwenwen authored
deepseek-r1-w4a8使用rmsquant融合算子及横向融合 See merge request dcutoolkit/deeplearing/vllm!205
-
wujl5 authored
-
zhuwenwen authored
V0.9.2 dev pd tbo See merge request dcutoolkit/deeplearing/vllm!204
-
xuxzh1 authored
-
xuxzh1 authored
-
zhuwenwen authored
-
zhuwenwen authored
[fix]修复eagle 创建cu_num_tokens类型错误问题 See merge request dcutoolkit/deeplearing/vllm!203
-
王敏 authored
-
