-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[None][chore] reduce the layers of the
devel docker image
#9077
opened Nov 11, 2025 by
MartinMarciniszyn
Loading…
1 task done
[TRTLLM-9175][test] ensure sampling is async
#9076
opened Nov 11, 2025 by
ixlmar
Loading…
1 task done
[None][feat] Add TRTLLM_NIXL_KVCACHE_BACKEND environment variable for NIXL backend selection
#9075
opened Nov 11, 2025 by
zackyoray
Loading…
1 task done
[None][infra] Waive other timeout cases in unittest/_torch/speculative
#9074
opened Nov 11, 2025 by
EmmaQiaoCh
Loading…
1 task done
[None][fix] Update the attention layers counting for Qwen3-next.
#9072
opened Nov 11, 2025 by
nv-guomingz
•
Draft
[https://nvbugs/5568991][test] Remove Phi-3 models
#9066
opened Nov 11, 2025 by
yufeiwu-nv
Loading…
1 task done
[None][feat] Add Qwen3-Next to layer-wise benchmarks
#9065
opened Nov 11, 2025 by
yuantailing
Loading…
1 task done
[None][fix] Remove unnecessary attention workspace memory check
#9064
opened Nov 11, 2025 by
jiaganc
Loading…
1 task done
[TRTLLM-9018][infra] add mirror for Build-Docker-Images stage
#9063
opened Nov 11, 2025 by
ZhanruiSunCh
Loading…
1 task done
[None][fix] AutoDeploy: update nano3 accuracy test
#9061
opened Nov 11, 2025 by
lucaslie
Loading…
1 task done
[None][feat] support Qwen3-VL dense model in pytorch backend
Community want to contribute
PRs initiated from Community
#9060
opened Nov 11, 2025 by
Nekofish-L
Loading…
1 task done
[TRTLLM-8274][feat] Check if executor is shutdown in /health entrypoint
#9057
opened Nov 11, 2025 by
JunyiXu-nv
Loading…
1 task done
[https://nvbugs/5627710][fix] Fix synchronization bugs in KvCacheTransferManager that can cause corrupted blocks
#9056
opened Nov 11, 2025 by
thorjohnsen
Loading…
1 task done
[TRTLLM-9259][perf] Use torch.compile to fuse copy + layernorm within the LayerNorm module
#9052
opened Nov 10, 2025 by
chang-l
Loading…
1 task done
[None][chore] Remove is_disaggregated param in executor request queue
#9049
opened Nov 10, 2025 by
pcastonguay
Loading…
1 task done
[https://nvbugs/5647400] [fix] Enlarged the allreduce workspace size to 64MB. Added strategy to AD config.
#9046
opened Nov 10, 2025 by
MrGeva
Loading…
1 task done
[None][feat] Add MTP>1 support for DS-v3.2
#9045
opened Nov 10, 2025 by
lfr-0531
Loading…
1 task done
[TRTLLM-9159][doc] Add KV Connector docs
Doc
<NV>TRTLLM's textual/illustrative materials: API refs, guides, tutorials. Improvement & clarity.
#9043
opened Nov 10, 2025 by
Shunkangz
Loading…
1 task done
[None][Infra] Revert "[TRTLLM-8994][infra] upgrade to DLFW 25.10 and pytorch 2.9.0 / triton 3.5.0 (#8838)"
#9039
opened Nov 10, 2025 by
ZhanruiSunCh
Loading…
1 task done
[TRTLLM-9053, TRTLLM-9054][feat] Draft: support accuracy test and install from wheel
#9038
opened Nov 10, 2025 by
zerollzeng
Loading…
1 task
[None][chore] Prevent negative
max_tokens passed into tllm request
#9037
opened Nov 10, 2025 by
JunyiXu-nv
Loading…
1 task done
Previous Next
ProTip!
Updated in the last three days: updated:>2025-11-08.