- 14 Jul, 2025 1 commit
-
-
zhuwenwen authored
[fix]1.优化mtp代码,解决prefix-caching不兼容问题; 2.修复v1 engine从tokenizer config中读取max_model_len导致长文本输入报错 See merge request dcutoolkit/deeplearing/vllm!158
-
- 12 Jul, 2025 4 commits
- 11 Jul, 2025 3 commits
- 10 Jul, 2025 6 commits
- 09 Jul, 2025 2 commits
- 07 Jul, 2025 6 commits
- 05 Jul, 2025 1 commit
-
-
zhuwenwen authored
-
- 04 Jul, 2025 2 commits
- 03 Jul, 2025 7 commits
- 02 Jul, 2025 1 commit
-
-
zhuwenwen authored
-
- 01 Jul, 2025 2 commits
- 30 Jun, 2025 3 commits
- 27 Jun, 2025 2 commits