GitLab

fuse_moe_fp8接入marlin算子
fix(v1)：修复抢占恢复时 BlockTable 溢出
feat(moe)：新增 VLLM_USE_MOE_W16A16_TRTION 强制 Triton MoE
fix: 解决原版0消耗chunk-prefill崩溃问题
fp8增加fused_moe_gate参数

[opt] 优化epsp代码, 零消耗添加epsp
update VLLM_USE_FUSED_RMS_ROPE=0 (default). for qwen3, VLLM_USE_FUSED_RMS_ROPE=1 (default)
feat(moe/marlin): Marlin W16A16 MoE 自动探测并预打包（去掉手动开关）
perf(qwen3): 融合 q/k RMSNorm + RoPE
fused_moe_fp8接入lmslim

[feat]1.优化ep sequence parallel,区分主模型和mtp逻辑;2.ep sequence parallel添加cudagraph padding到tp_size;3.修复共享专家和deepep combine overlap

This reverts merge request !219