"tests/vscode:/vscode.git/clone" did not exist on "32e45636e3d7e02615facc8c63645ce4ac1d7e11"
  • zhuwenwen's avatar
    [feat] 适配block和channel fp8, 添加dp attention功能 · 2b7b1a31
    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
    2b7b1a31
_custom_ops.py 99.1 KB