[pull] main from NVIDIA:main#556

Merged

pull[bot] merged 6 commits intoLarryXFly:mainfrom

Oct 28, 2025

Commits on Oct 28, 2025

[https://nvbugs/5556475] [fix] Fix the `tensorrt_llm_bls` model to correctly return the outputs for `num_input_tokens` and `num_output_tokens` (#8150)
pskiran1
authored
[None][fix] Change Ray submit() to use async RPC (#8636)
hchings
authored
[None][test] Add gpt_oss_20b Model to Sanity Perf Test (#8265)
yufeiwu-nv
authored
[TRTLLM-7835][test] add default sample config for perf test (#8523)
ruodil
authored
[https://nvbugs/5564465][test] ensure deepseek_v3_lite isl + osl < max_seq_len (#8565)
ruodil
authored
[None][fix] fix EPLB init hang (#8649)
dongxuy04
authored