- 10 Feb, 2026 1 commit
-
-
zhuwenwen authored
[pd] 修改非堆成切分的判断, pd分离使用默认调度，set VLLM_USE_PD_SPLIT=1 [perf](fused-moe): 预打包 Marlin W16A16 MoE 权重，降低 warmup 显存峰值 [fix]修复丢弃MTP代码报错，pp+chunkprefill多并发input ids更新bug, 修复不开启融合图的断言错误, PP 场景 decode 阶段 token 被误丢弃导致卡住
-
- 25 Dec, 2025 1 commit
-
-
gaoqiong authored
-
- 22 Dec, 2025 3 commits
- 18 Dec, 2025 2 commits
- 17 Dec, 2025 2 commits
- 16 Dec, 2025 1 commit
-
-
yangql authored
-
- 15 Dec, 2025 2 commits
- 10 Dec, 2025 1 commit
-
-
王敏 authored
-
- 08 Dec, 2025 1 commit
-
-
王敏 authored
-
- 02 Dec, 2025 1 commit
-
-
王敏 authored
-
- 26 Nov, 2025 2 commits
- 21 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 20 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 19 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 18 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 15 Nov, 2025 1 commit
-
-
王敏 authored
-
- 13 Nov, 2025 2 commits
- 11 Nov, 2025 1 commit
-
-
wanglong3 authored
-
- 10 Nov, 2025 1 commit
-
-
SAC_fanth authored
-
- 07 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 03 Nov, 2025 2 commits
- 01 Nov, 2025 1 commit
-
-
王敏 authored
-
- 27 Oct, 2025 1 commit
-
-
王敏 authored
-
- 15 Oct, 2025 3 commits
- 13 Oct, 2025 1 commit
-
-
王敏 authored
-
- 30 Sep, 2025 2 commits
- 26 Sep, 2025 1 commit
-
-
zhuwenwen authored
add shared_output and routed_scaling_factor of CompressedTensorsW8A8Int8MoEMethod
-
- 25 Sep, 2025 2 commits
