Skip to content

[https://nvbugs/6567554][fix] Mirror KVCacheManagerV2.max_blocks_per_seq arithmetic in the harness budget… - #17373

Open
trtllm-agent wants to merge 1 commit into
NVIDIA:mainfrom
tensorrt-cicd:repair-bot-bug6567554
Open

[https://nvbugs/6567554][fix] Mirror KVCacheManagerV2.max_blocks_per_seq arithmetic in the harness budget…#17373
trtllm-agent wants to merge 1 commit into
NVIDIA:mainfrom
tensorrt-cicd:repair-bot-bug6567554

[nvbugs/6567554][fix] Fix layer-wise benchmark GEN phase for DeepSeek-V4

1296ac6
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Sep 21, 2026 in 1s

DCO

All commits are signed off!

View more details on DCO