Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[TRTLLM-12950][perf] DSv4 follow-up: DeepGEMM and MegaMoE
#15632
opened Jun 25, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[TRTLLM-12622][feat] Reland: Add native post-processing hook to trtllm-serve
api-compatible
Accepted LLM API contract change that is backwards-compatible
#15631
opened Jun 25, 2026 by
xwang233
Collaborator
Loading…
1 task done
[None][infra] AutoDeploy: Add trtllm runner for standalone llm-c
#15630
opened Jun 25, 2026 by
bmarimuthu-nv
Collaborator
Loading…
1 task done
[TRTLLM-12982][chore] improve multi-item scoring request validation
#15627
opened Jun 25, 2026 by
ixlmar
Collaborator
Loading…
1 task done
[None][perf] DSv4 follow-up: autotuner updates
#15626
opened Jun 25, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[None][perf] DSv4 follow-up: disagg routing improvements
#15625
opened Jun 25, 2026 by
lfr-0531
Collaborator
Loading…
1 task done
[TRTLLM-13629][test] Optimize MoE CI test-db
#15624
opened Jun 25, 2026 by
xxi-nv
Collaborator
Loading…
[#15565][fix] AutoDeploy: Fix Super MTP IMA introduced by checkpointing replay
#15622
opened Jun 25, 2026 by
galagam
Collaborator
Loading…
1 task done
[https://nvbugs/6242591][fix] Fix bugs in Beam Search kernels
#15621
opened Jun 25, 2026 by
wili-65535
Collaborator
•
Draft
1 task done
[None][feat] Disaggregated KV-cache bounce transfer
#15618
opened Jun 25, 2026 by
Shixiaowei02
Collaborator
Loading…
1 task done
[None][test] Add Kimi-K2.5 disaggregated GSM8K accuracy test
#15617
opened Jun 25, 2026 by
Shixiaowei02
Collaborator
Loading…
1 task done
[TRTLLM-13613][test] Trim duplicated and dead multimodal accuracy tests from pre-merge CI
#15615
opened Jun 25, 2026 by
Wanli-Jiang
Collaborator
Loading…
1 task done
[None][infra] take test durations into account to determine cbts splits num
#15614
opened Jun 25, 2026 by
crazydemo
Collaborator
Loading…
1 task done
[TRTLLM-13409][feat] hard-exit on HangDetector fire + cross-rank propagation
#15612
opened Jun 25, 2026 by
JunyiXu-nv
Collaborator
•
Draft
1 task
[https://nvbugs/6368480][fix] Cache the SM count once in FmhaDispatcher's constructor and reuse the cached…
#15611
opened Jun 25, 2026 by
chenfeiz0326
Collaborator
Loading…
2 tasks done
[None][feat] add in-process NeMo-Skills benchmarks and Nemotron-3-Super guards
#15608
opened Jun 25, 2026 by
Wanli-Jiang
Collaborator
•
Draft
1 task done
[https://nvbugs/6293536][fix] Stage v2 KV block offsets through fresh host buffers
#15607
opened Jun 25, 2026 by
thorjohnsen
Collaborator
•
Draft
[None][chore] Update .gitattributes
#15606
opened Jun 25, 2026 by
ziyixiong-nv
Collaborator
Loading…
1 task
[None][fix] Align GPTOSS router tokenization and disagg draft scheduling
#15605
opened Jun 24, 2026 by
SimengLiu-nv
Collaborator
Loading…
1 task done
[None][infra] add error hints to PR title check
#15604
opened Jun 24, 2026 by
tburt-nv
Collaborator
Loading…
1 task done
[None][feat] VisualGen: enable CUDA graph capture with torch.compile
#15603
opened Jun 24, 2026 by
chang-l
Collaborator
Loading…
6 tasks done
[None][infra] Add support to run NGC container scanning in pre-merge
#15602
opened Jun 24, 2026 by
yuanjingx87
Collaborator
Loading…
1 task
ProTip!
What’s not been updated in a month: updated:<2026-05-25.