[pull] main from NVIDIA:main#1316

Merged

pull[bot] merged 10 commits into

LarryXFly:mainfrom

May 29, 2026

Commits on May 29, 2026

[TRTLLM-12982][perf] remove sync after FlashInfer attention plan() (#14634)
ixlmar
authored
[https://nvbugs/6156233][test] unwaive GPT-OSS dflash test since bug has been closed as fix unknown (#14713)
dongfengy
authored
[TRTLLM-12901][fix] cap per-rank max_num_active_requests by max_num_tokens under attention DP (#14481)
xwang233
authored
[None][feat] Enable NVFP4 KV cache support in trtllm-gen attention (#12544)
yihwang-nv
authored
[https://nvbugs/6185480][fix] autodeploy unwaive the test (#14716)
nvchenghaoz
authored
[https://nvbugs/6136737][fix] Propagate external SWA window to FMHA kernel in V2 KV cache (#13719)

tensorrt-cicd
and
thorjohnsen
authored
[https://nvbugs/5996024][fix] Enforce trust_remote_code flag (#13527)
yibinl-nvidia
authored
[https://nvbugs/5979710][fix] Bound transfer destinations (#13525)
yibinl-nvidia
authored
[None][fix] Resolve NVML device index mismatch in get_numa_aware_cpu_affinity when CUDA_VISIBLE_DEVICES is set (#12985)

YPxHolic
and
karljang
authored
[None][infra] revert #13607 (#14757)
tburt-nv
authored