GitLab

[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

解决w8a8 pp16开启marlin的oom问题

Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>

Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: ElizaWszola <ewszola@redhat.com>

Signed-off-by: jiang1.li <jiang1.li@intel.com>

Signed-off-by: mgoin <mgoin64@gmail.com>

Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: Haoyang Li <Haoyang.Li@amd.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>

Signed-off-by: yewentao256 <zhyanwentao@126.com>

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>

Signed-off-by: mgoin <mgoin64@gmail.com>

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>

Signed-off-by: Randall Smith <Randall.Smith@amd.com>

Signed-off-by: Andy Xie <andy.xning@gmail.com>

Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

Signed-off-by: Chiyue Wei <chiyuew@nvidia.com>
Co-authored-by: Chiyue Wei <chiyuew@nvidia.com>

Signed-off-by: simon-mo <simon.mo@hey.com>

[ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control blockscale tensor allocation (#18160)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

Implements dual-chunk-flash-attn backend for dual chunk attention with sparse attention support (#11844)

Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>