- 05 Aug, 2025 6 commits
- 04 Aug, 2025 4 commits
- 02 Aug, 2025 1 commit
-
-
zhuwenwen authored
-
- 01 Aug, 2025 13 commits
-
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
-
gaoqiong authored
-
zhuwenwen authored
-
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
[fix]避免mla中cudagraph的适配影响非并行解码的逻辑 See merge request dcutoolkit/deeplearing/vllm!165
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
[feat]支持v1 engine mtp cudagraph See merge request dcutoolkit/deeplearing/vllm!164
-
- 31 Jul, 2025 8 commits
- 30 Jul, 2025 4 commits
- 29 Jul, 2025 4 commits