[pull] main from NVIDIA:main#1491

Merged

pull[bot] merged 9 commits into

LarryXFly:mainfrom

Jul 17, 2026

Commits on Jul 17, 2026

[TRTLLM-14054][perf] Reduce per-step host preparation overhead in the PyTorch executor decode path (#16313)
kaiyux
authored
[https://nvbugs/6404567][fix] Clamp piecewise cudagraph captures to the reachable ceiling instead of force-appending it (#16256)

dongfengy
and
claude
authored
[https://nvbugs/6272673][chore] Unwaive DeepSeek V3 Lite NVFP4 test (#16398)
yuxianq
authored
[None][fix] DSA CuteDSL paged-MQA-logits: persistent output buffer (CUDA-graph stale-pointer IMA) (#16307)
Tabrizian
authored
[None][fix] Fix unfused RoPE for yarn models: double rotation and GPT-OSS pairing (#16378)
Hudayday
authored
[None][test] Update LLM performance test cases to use increased input/output lengths (#16538)
yufeiwu-nv
authored
[https://nvbugs/6336747][fix] Honor GenerationResult timeout (#16453)
2ez4bz
authored
[https://nvbugs/6460072][fix] Split the caller — for `use_lm_head_tp_in_adp and is_all_greedy_sample`, keep… (#16440)
trtllm-agent
authored
[None][infra] Add blossom-ci authorized users (#16541)

yiqingy0
and
yiqingy
authored