- 25 Nov, 2025 1 commit
-
-
lizhigong authored
-
- 24 Nov, 2025 1 commit
-
-
lizhigong authored
-
- 23 Nov, 2025 2 commits
- 21 Nov, 2025 9 commits
-
-
zhuwenwen authored
deepseek_v2_w8a8 增加 silu_mul_quant融合 See merge request dcutoolkit/deeplearing/vllm!265
-
wujl5 authored
-
zhuwenwen authored
set VLLM_USE_LIGHTOP_FILL_MOE_ALIGN=1, VLLM_USE_OPT_ZEROS=1 and VLLM_USE_PP_SYNC=1
-
zhuwenwen authored
feat: pp mtp加入零消耗调度,加入环境变量VLLM_USE_ZERO_MTP,默认打开 See merge request dcutoolkit/deeplearing/vllm!264
-
jujl1 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
-
zhuwenwen authored
-
- 20 Nov, 2025 9 commits
-
-
zhuwenwen authored
feat: pipeline_parallel新增pp域请求数均衡,VLLM_USE_PP_BALANCE控制,默认开启 See merge request dcutoolkit/deeplearing/vllm!262
-
jujl1 authored
-
-
zhuwenwen authored
-
zhuwenwen authored
deepseek_v2_w4a8模型forward_CRQ分支逻辑增加slilu_mul_quant融合 See merge request dcutoolkit/deeplearing/vllm!261
-
zhuwenwen authored
-
wujl5 authored
-
wujl5 authored
-
wujl5 authored
-
- 19 Nov, 2025 8 commits
- 18 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 17 Nov, 2025 5 commits
- 14 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 13 Nov, 2025 3 commits