COMMITS
August 26, 2026
M
[TRTLLMINF-339][infra] Enable BOLT profile-gen producer (job + cadence + promote) (#18212)
Matt Lefebvre committed
P
[None][fix] Drop the unbound is_idle guard left in the idle disagg CTX reap (#18263)
Pranav Shrestha committed
Y
[None][infra] Set --platform when retagging CI image (#18208)
Yuanjing Xue committed
D
B
[None][ci] waive pre-existing test failures on main (#18191)
brnguyen2 committed
I
[None][fix] Simplify idle disagg KV transfer progress check (#17324)
Iman Tabrizian committed
T
[None][infra] Waive 1 failed cases for main in pre-merge 56793 (#18258)
TensorRT LLM AI Agent committed
A
[https://nvbugs/6327718][fix] Drain EPD thread pool before proxy shutdown (#17988)
Aswin Visva committed
A
[None][fix] Multimodal Mixin Guided Decoder Delegation (#18162)
Aswin Visva committed
Y
[https://nvbugs/6579626][perf] Fallback small BF16 context batches (#18196)
Yihan Wang committed
J
[None][perf] Compute response GPU timings once per batch (#18053)
Jin Li committed
J
L
[TRTLLM-15293][perf] Add self-sampling (GVR V2) top-K decode kernels (#17821)
longcheng-nv committed
Y
[https://nvbugs/6422432][fix] Unwaive testcase (#17947)
YihuiLu512 committed
Q
[None][ci] disable autodeploy test stages (#18107)
QI JUN committed
Y
[None][chore] Add Top-K code owners (#18246)
Yuxian Qiu committed
J
S
[https://nvbugs/6647310][chore] Unwaive TestLagunaXS::test_nvfp4 (#18219)
sunnyqgg committed
S
[None][feat] Add nvfp4 situ moe cubins (#17940)
Song Rong committed
T
[None][infra] Waive 1 failed cases for main in pre-merge 56702 (#18245)
TensorRT LLM AI Agent committed
L
P
[https://nvbugs/6596590][fix] Densify warmup mesh for sparse fmha kernel (#17961)
Pengbo Wang committed
F
[None][fix] Stabilize Gemma4 FA2 CUDA Graph decode on Hopper (#18002)
Fanrong Li committed
F
[https://nvbugs/6647349][fix] Replace FuzzyWuzzy with RapidFuzz (#18201)
Fanrong Li committed
I
[None][infra] Fix CBTS skip-rate calculation method (#16467)
Ivy Zhang committed
T
[https://nvbugs/6561778][fix] Fence all ranks before pytest launch in multi-node slurm_run.sh (#17372)
TensorRT LLM AI Agent committed
T
[None][infra] Waive 1 failed cases for main in pre-merge 56631 (#18224)
TensorRT LLM AI Agent committed
T
[None][infra] Waive 7 failed cases for main in post-merge 2927 (#18230)
TensorRT LLM AI Agent committed
T
[None][infra] Waive 1 failed cases for main in pre-merge 56649 (#18229)
TensorRT LLM AI Agent committed
F
[None][test] Remove deepseek v32 test cases on the qa side for disagg multinode perf testing (#18225)
fredricz-20070104 committed