- 30 May, 2025 1 commit
-
-
zhuwenwen authored
-
- 29 May, 2025 8 commits
-
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
增加w8a8 线性gemm triton优化 See merge request dcutoolkit/deeplearing/vllm!128
-
zhuwenwen authored
-
lizhigong authored
-
gaoqiong authored
-
zhuwenwen authored
-
zhuwenwen authored
[feat]量化模型添加支持 moe_fused_gate kernel,并使用VLLM_ENABLE_MOE_FUSED_GATE环境变量控制开关,默认打开 See merge request dcutoolkit/deeplearing/vllm!127
-
- 28 May, 2025 8 commits
-
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
修复0.8.5 config找不到的bug See merge request dcutoolkit/deeplearing/vllm!126
-
zhuwenwen authored
[feat]适配sgl moe_fused_gate kernel See merge request dcutoolkit/deeplearing/vllm!125
-
- 27 May, 2025 3 commits
- 26 May, 2025 12 commits
-
-
zhuwenwen authored
-
zhuwenwen authored
debug and fix tbo error in mtp See merge request dcutoolkit/deeplearing/vllm!124
-
lizhigong authored
-
zhuwenwen authored
fix tbo support deepseek mtp See merge request dcutoolkit/deeplearing/vllm!123
-
lizhigong authored
-
zhuwenwen authored
V0.8.5.post1 dev wm See merge request dcutoolkit/deeplearing/vllm!122
-
王敏 authored
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
Update sequence.py fix assert error。 See merge request dcutoolkit/deeplearing/vllm!121
-
lizhg1 authored
-
zhuwenwen authored
-
- 23 May, 2025 6 commits
- 22 May, 2025 2 commits
-
-
zhuwenwen authored
-
zhuwenwen authored
Merge branch 'v0.8.5.post1-dev' of http://112.11.119.99:10068/dcutoolkit/deeplearing/vllm into v0.8.5.post1-dev
-