-
Notifications
You must be signed in to change notification settings - Fork 2.2k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[TRTLLM-11707][feat] LTX-2 Cuda Graph Support
VisualGen
#12603
opened Mar 31, 2026 by
yibinl-nvidia
•
Draft
1 task
[TRTLLM-11608][feat] Chunked KV cache transfer with early block release
#12602
opened Mar 30, 2026 by
chienchunhung
•
Draft
1 task done
[None][infra]User/yuanjingx/bump tornado and black in container
#12600
opened Mar 30, 2026 by
yuanjingx87
Loading…
1 task done
[#11538][fix] Enable sliding window attention for Mistral/Mixtral
#12597
opened Mar 30, 2026 by
karljang
Loading…
1 task done
[#12595][feat] Emit initial KV cache stats at startup for external metric scrapers
Community want to contribute
PRs initiated from Community
#12596
opened Mar 30, 2026 by
BenjaminBraunDev
Loading…
[None][infra] Bump etcd to 3.6.9 to involve grpc fix
#12594
opened Mar 30, 2026 by
yuanjingx87
Loading…
1 task
Add early validation for unsupported MXFP4/NVFP4 quantization on Hopper (SM90)
Community want to contribute
PRs initiated from Community
#12591
opened Mar 30, 2026 by
aashirvad08
Loading…
[None][chore] Remove Model Registry Check from workflows, the check already runs in pre-commit
#12590
opened Mar 30, 2026 by
tcherckez-nvidia
Loading…
1 task done
[None][infra] Waive 1 failed cases for main in pre-merge 31714
#12589
opened Mar 30, 2026 by
ZhanruiSunCh
Loading…
[TRTLLM-11540 ][feat] Support rejection sampling in EAGLE3 dynamic tree
#12588
opened Mar 30, 2026 by
zhaoyangwang-nvidia
•
Draft
1 task done
[None][feat] Add --custom_tokenizer CLI option to trtllm-bench
#12586
opened Mar 30, 2026 by
qiaoxj07
Loading…
3 tasks done
[https://nvbugs/5989923][fix] fix test_py_cache_transceiver_mp
#12584
opened Mar 30, 2026 by
chuangz0
Loading…
1 task done
[None][chore] Use TRTLLM_NAMESPACE_BEGIN macro instead of non-inline namespace '_v1' workaround
#12582
opened Mar 30, 2026 by
yihwang-nv
Loading…
1 task done
[https://nvbugs/5983390][perf] Reduce host overhead caused by torch.compile in speculative decoding.
#12581
opened Mar 30, 2026 by
hyukn
Loading…
1 task done
[https://nvbugs/5997543][fix] unwaive test_disaggregated_overlap_transceiver_runtime_python
#12580
opened Mar 30, 2026 by
chuangz0
Loading…
1 task done
[None][doc] Update C++ coding guidelines.
#12577
opened Mar 29, 2026 by
hnover-nv
Loading…
1 task done
[https://nvbugs/5997090][fix] Fix Pyxis Error in Disagg Perf Test
#12575
opened Mar 29, 2026 by
chenfeiz0326
Loading…
1 task done
[https://nvbugs/5596343][fix] Re-enable passing tests
#12574
opened Mar 29, 2026 by
dongfengy
Loading…
1 task done
[None][fix] Fix DSACacheManager and RocketCacheManager KV cache estimation ignoring num_layers for draft models
#12571
opened Mar 29, 2026 by
lancelly
Loading…
[https://nvbugs/5850183][fix] Re-enable passing tests
#12568
opened Mar 29, 2026 by
dongfengy
Loading…
1 task done
Previous Next
ProTip!
Adding no:label will show everything without a label.