[pull] main from NVIDIA:main#1462

Merged

pull[bot] merged 14 commits into

LarryXFly:mainfrom

Jul 9, 2026

Commits on Jul 9, 2026

[https://nvbugs/6316983][fix] Fix RoPE support in flashinfer trtllm-gen backend (#15661)
yihwang-nv
authored
[None][perf] Port remaining DeepSeek V4 optimizations to main (#16028)

authored
[None][infra] Automate and gate LLM args telemetry manifest updates (#16013)
venkywonka
authored
[None][infra] Waive 4 failed cases for main in post-merge 2827 (#16169)
trtllm-agent
authored
[DEP-950][feat] add multi-rank sleep/wakeup support to MPI executor path (#14636)
hhzhang16
authored
[TRTLLM-13977][fix] Fix NT3 NVFP4 perf regression in Blackwell (#16031)
xuantengh
authored
[None][docs] Default GitHub CLI config directory non-interactively (#15978)
bobboli
authored
[None][test] DSv4 PR-6 coverage and import safety (#15710)

lfr-0531
and
jiaganc
authored
[TRTLLM-14155][fix] Revert host-side greedy stop checks from #15920 (#16163)
mingyangHao
authored
[TRTLLMINF-144][infra] Only display rerun test results in the rerun report (#15619)

yiqingy0
and
yiqingy
authored
[TRTLLM-13784][chore] Remove legacy TensorRT-engine Triton backend (#15907)

Wanli-Jiang
and
tburt-nv
authored
[None][test] Remove H200 and RTX6000-D for QA perf Test (#16183)
yufeiwu-nv
authored
[None][test] Reduce Nemotron V3 Super/Ultra pre-merge test cases (#16122)
nv-guomingz
authored
[None][infra] Waive 2 failed cases for main in pre-merge 46981 (#16186)
trtllm-agent
authored