Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
638 Open 8,092 Closed
638 Open 8,092 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[None][fix] Replace assertions with warnings for unsupported logits/logprobs in speculative sampler Community want to contribute PRs initiated from Community
#12547 opened Mar 25, 2026 by yifjiang Loading…
3 tasks
[None][feat] Add production-level Prometheus metrics (iteration stats, config info, token counters, phase histograms) Community want to contribute PRs initiated from Community
#12545 opened Mar 25, 2026 by nvyutwu Loading…
5 tasks
4
[None][feat] Enable NVFP4 KV cache support in trtllm-gen attention
#12544 opened Mar 25, 2026 by yihwang-nv Loading…
1 task
@yihwang-nv
8
[TRTLLMINF-37][feat] Add CI agent failure analysis to L0_MergeRequest…
#12543 opened Mar 25, 2026 by dpitman-nvda Loading…
1 task done
@dpitman-nvda
4
[https://nvbugs/6018172][fix] Add synchronization calls to warmup when host cache offloading is active
#12539 opened Mar 25, 2026 by longlee0622 • Draft
1 task
@longlee0622
1
[TRTLLM-11318][feat] move VisualGen APIs to a separate dir VisualGen
#12538 opened Mar 25, 2026 by zhenhuaw-me Loading…
1 task done
@zhenhuaw-me
8
[None][feat] Add Mamba2 MTP SSM cache CUDA kernel for tree-based speculative decoding
#12537 opened Mar 25, 2026 by JadoTu Loading…
1 task done
@JadoTu
9
[None][test] Enhance performance tests by adding GPU availability check in test_perf.py
#12535 opened Mar 25, 2026 by yufeiwu-nv Loading…
1 task done
@yufeiwu-nv
5
[None][doc] Add MoE developer guide for fused_moe module
#12534 opened Mar 25, 2026 by xxi-nv Loading…
2 tasks done
@xxi-nv
5
[https://nvbugs/5989920][test] Unwaive DeepSeekV3 nvfp4 mtp3_fp8kv_chunked test
#12533 opened Mar 25, 2026 by yizhang-nv Loading…
1 task done
@yizhang-nv
3
[None][docs] Add docstrings to cpp_custom_ops, model_config, and llm_args
#12532 opened Mar 25, 2026 by longcheng-nv Loading…
1 task done
@longcheng-nv
11
[TRTLLM-10061][feat] Add support of linear attention state for C++ KV cache manager
#12531 opened Mar 25, 2026 by VALLIS-NERIA Loading…
2 tasks done
@VALLIS-NERIA
10
[https://nvbugs/5879577][fix] Fix KeyError in DeepSeekV3Lite FP8 MTP weight loading
#12530 opened Mar 25, 2026 by sunnyqgg Loading…
3 tasks done
@sunnyqgg
4
[https://nvbugs/6007967][fix] fix disagg pp hang issue
#12528 opened Mar 25, 2026 by bo-nv Loading…
1 task
@bo-nv
6
[https://nvbugs/6007197][fix] Adjust RocketKV test threshold
#12527 opened Mar 25, 2026 by heyuhhh Loading…
1 task done
@heyuhhh
4
[TRTLLM-11657][feat] Conversation affinity disagg router
#12526 opened Mar 25, 2026 by reasonsolo • Draft
1 task
@reasonsolo
[None][feat] Disable shared paged index in flashinfer trtllm-gen fmha kernel and unify kv cache buffer calculation with thop.attention
#12525 opened Mar 25, 2026 by yihwang-nv Loading…
1 task done
@yihwang-nv
22
[None][doc] Fix duplicate words in comments
#12524 opened Mar 25, 2026 by YihuiLu512 Loading…
1 task done
@YihuiLu512
10
[https://nvbugs/6011517][fix] Fix autotuner OOM for trtllmGen MoE runners at large context length
#12523 opened Mar 25, 2026 by hyukn Loading…
1 task done
@hyukn
4
Adds a LMCache v1 KV connector example (llm_lmcache_connector.py) that Community want to contribute PRs initiated from Community
#12522 opened Mar 25, 2026 by feixiangpeng Loading…
1 task
9
[None][fix] Fix _waiting_requests to use compute tokens with KV cache reuse
#12521 opened Mar 25, 2026 by lancelly Loading…
@lancelly
9
[None][test] Add different input-output of eagle cases on Spark
#12520 opened Mar 25, 2026 by JennyLiu-nv Loading…
1 task done
@JennyLiu-nv
7
[None][feat] Add Blackwell MLA backend selection
#12519 opened Mar 25, 2026 by bmarimuthu-nv • Draft
1 task
@bmarimuthu-nv
[#11992][fix] Support include_stop_token_in_output in gRPC request manager Community want to contribute PRs initiated from Community
#12517 opened Mar 24, 2026 by CatherineSue Loading…
3 tasks done
6
[https://nvbugs/6015329][fix] Use model-level warmup cache key for visual gen pipelines VisualGen
#12516 opened Mar 24, 2026 by karljang Loading…
2 tasks done
@karljang
16
ProTip! no:milestone will show everything without a milestone.