Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][chore] Add multinode e2e and accuracy cases on DGX-Spark
#12110
opened Mar 11, 2026 by
JennyLiu-nv
Loading…
1 task done
[TRTLLM-11288][feat] Configurable warmup shapes for VisualGen
#12107
opened Mar 11, 2026 by
luyiyun1021
Loading…
1 task done
[TRTLLM-10303][feat] Deprecate trtllm-serve CLI options
#12106
opened Mar 11, 2026 by
JunyiXu-nv
Loading…
1 task done
[TRTLLM-10076][feat] Serve CLI improvements: renames, new flags, and mm_embedding_serve enhancements
#12105
opened Mar 11, 2026 by
JunyiXu-nv
Loading…
1 task done
[TRTLLM-10077][feat] Add 'auto' option for tool and reasoning parsers
#12104
opened Mar 11, 2026 by
JunyiXu-nv
Loading…
1 task done
[None][chore] Add explicit error for intermediate size misalignment with fp8 block size
#12101
opened Mar 11, 2026 by
leslie-fang25
Loading…
1 task done
[None][fix] Enforce minimum NVSHMEM_QP_DEPTH of 128 for DeepEP low latency
#12100
opened Mar 11, 2026 by
Tabrizian
Loading…
1 task done
[https://nvbugs/5963423][fix] Fix kv token estimation when ADP is on.
#12099
opened Mar 11, 2026 by
dominicshanshan
Loading…
1 task done
WIP: [TRTLLM-9911] [doc] Update Perf-Overview.md for Release 1.2
Doc
<NV>TRTLLM's textual/illustrative materials: API refs, guides, tutorials. Improvement & clarity.
Release Blocker
PRs that blocking the final release build or branching out the release branch
#12098
opened Mar 11, 2026 by
zbpatel
Loading…
1 task
[None][test] fix perf test cases issue of incorrect match
#12096
opened Mar 11, 2026 by
ruodil
Loading…
1 task done
[TRTLLM-9523][feat] Additional adaptation to manager v2 (step 6)
#12095
opened Mar 11, 2026 by
Shixiaowei02
•
Draft
1 task
[None][chore] Update flashinfer to 0.6.6
#12094
opened Mar 11, 2026 by
yihwang-nv
•
Draft
1 task done
[https://nvbugs/5826604][test] Remove test waive for Llama3.1 8B bfloat16 4gpu timeout …
#12092
opened Mar 11, 2026 by
syuoni
Loading…
1 task done
[https://nvbugs/5948539][fix] Fix disagg gen-only benchmark
#12091
opened Mar 10, 2026 by
Tabrizian
Loading…
1 task done
Draft - Don't Review - AD Deepseek-V3-Lite and mla enablement
#12089
opened Mar 10, 2026 by
MrGeva
Loading…
1 task
[TRTLLMINF-11][chore] Change image used for Preparation step of CI
#12086
opened Mar 10, 2026 by
dpitman-nvda
Loading…
1 task done
[None][chore] Unwaiving disagg tests failing with address in use error
#12085
opened Mar 10, 2026 by
pcastonguay
Loading…
1 task done
[TRTLLM-11394][feat] Add CudaVmmArena: contiguous GPU memory via CUDA VMM API
#12084
opened Mar 10, 2026 by
thorjohnsen
•
Draft
1 task done
[None][test] Add speculative decoding test with exclude_input_in_output=true
#12080
opened Mar 10, 2026 by
StanleySun639
Loading…
1 task done
[None][feat] CuteDSL MOE: Add raster along M/N support for blockscaled contiguous backbone kernel
#12079
opened Mar 10, 2026 by
liyuhannnnn
Loading…
1 task done
[TRTLLM-11289][feat] Integrate CuteDSL's bf16 dense GEMMs
#12074
opened Mar 10, 2026 by
peaceh-nv
Loading…
ProTip!
Mix and match filters to narrow down what you’re looking for.