- 11 Feb, 2026 1 commit
-
-
zhuwenwen authored
-
- 10 Feb, 2026 3 commits
- 09 Feb, 2026 1 commit
-
-
zhuwenwen authored
-
- 06 Feb, 2026 1 commit
-
-
guanyu1 authored
-
- 03 Feb, 2026 1 commit
-
-
wanglong3 authored
-
- 28 Jan, 2026 1 commit
-
-
laibao authored
增加环境变量开关,禁用 Marlin W16A16 MoE 路径 强制 Triton 且权重已是 Marlin packed 时给出明确报错 Marlin 支持探测改为 best-effort(不再依赖 VLLM_USE_LIGHTOP)
-
- 27 Jan, 2026 2 commits
- 26 Jan, 2026 2 commits
- 23 Jan, 2026 3 commits
- 22 Jan, 2026 1 commit
-
-
王敏 authored
-
- 21 Jan, 2026 7 commits
-
-
zhuwenwen authored
新增 VLLM_USE_FUSED_RMS_ROPE 分支,走 fused 路径 注册 torch.ops.vllm.rms_rotary_embedding_fuse(direct_register_custom_op) cos_sin_cache 自动转 device/dtype 并缓存,避免每次重复拷贝
-
zhuwenwen authored
for qwen3, VLLM_USE_FUSED_RMS_ROPE=1 (default)
-
wanglong3 authored
-
xiabo authored
-
lixh6 authored
-
xiabo authored
-
zhuwenwen authored
-
- 20 Jan, 2026 6 commits
-
-
laibao authored
- 使用 get_moe_cuda_marlin_config_w16a16(status) 判断 W16A16 Marlin MoE 是否可用 - 在 FusedMoE 初始化阶段计算并缓存 _marlin_w16a16_moe_enabled,满足条件时强制 use_nn_moe=False - 权重加载后按缓存结果进行一次性 Marlin pack;运行时按 packed 标记走 Marlin fast path - 删除 envs.py 中 VLLM_USE_MARLIN_W16A16_MOE 环境变量定义与解析逻辑
-
zhuwenwen authored
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
laibao authored
-
- 19 Jan, 2026 3 commits
- 16 Jan, 2026 3 commits
- 15 Jan, 2026 2 commits
- 14 Jan, 2026 3 commits