Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
690 Open 9,607 Closed
690 Open 9,607 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] ADP router crashes on serve when scheduling_params.attent…
#14267 opened May 18, 2026 by nv-guomingz Collaborator Loading…
1 task done
@nv-guomingz
3
[TRTLLM-12719][cbts] Add core code related rule
#14266 opened May 18, 2026 by crazydemo Collaborator Loading…
1 task done
@crazydemo
7
[None][feat] Pre-allocate multimodal encoder attention workspace api-compatible Accepted LLM API contract change that is backwards-compatible
#14264 opened May 18, 2026 by yechank-nvidia Collaborator • Draft
@yechank-nvidia
[None][feat] Generalize encoder pre-allocation to multiple modalities
#14263 opened May 18, 2026 by yechank-nvidia Collaborator • Draft
@yechank-nvidia
[None][chore] Auto-update test durations from post-merge
#14262 opened May 18, 2026 by tensorrt-cicd Collaborator Loading…
@tensorrt-cicd
5
[https://nvbugs/6185234][fix] DeepSeek-V3.2 tokenizer load on transformers 5.x
#14261 opened May 18, 2026 by Hudayday Collaborator Loading…
@Hudayday
8
[None][test] Waive 2 failed cases for main in QA CI
#14260 opened May 18, 2026 by xinhe-nv Collaborator Loading…
@xinhe-nv
3
[None][infra] Waive 1 failed cases for main in post-merge
#14259 opened May 18, 2026 by xinhe-nv Collaborator Loading…
@xinhe-nv
3
fix token_range_end add extra_kv_num_tokens
#14258 opened May 18, 2026 by chuangz0 Collaborator Loading…
1 task done
@chuangz0
[None][test] Waive 7 failed cases for main in QA CI
#14257 opened May 18, 2026 by xinhe-nv Collaborator • Draft
@xinhe-nv
[None][feat] Add swiglu clamp to CuteDSL NVF4 MOE FC1 kernels
#14256 opened May 18, 2026 by liyuhannnnn Collaborator Loading…
1 task done
@liyuhannnnn
8
[None][fix] Handle None kv_cache in add_dummy_requests deepseek-v4
#14255 opened May 18, 2026 by Shixiaowei02 Collaborator Loading…
1 task done
@Shixiaowei02
3
[None][fix] DSv4 o_a_proj: decouple from use_cute_dsl_blockscaling_bmm
#14254 opened May 18, 2026 by lishicheng1996-nv Collaborator Loading…
1 task done
@lishicheng1996-nv
[None][test] Waive 1 failed cases for main in QA CI
#14253 opened May 18, 2026 by xinhe-nv Collaborator • Draft
@xinhe-nv
[https://nvbugs/6185713][fix] Revert PR13758's code changes on Limiting maximum warmup token count
#14252 opened May 18, 2026 by chenfeiz0326 Collaborator Loading…
1 task done
@chenfeiz0326
7
[https://nvbugs/6180247][fix] fix cache transceiver for dsv4 branch deepseek-v4
#14251 opened May 18, 2026 by chuangz0 Collaborator Loading…
1 task done
@chuangz0
3
[None][perf] fuse quant into norm and rope deepseek-v4
#14250 opened May 18, 2026 by mingyangHao Collaborator • Draft
1 task
@mingyangHao
[https://nvbugs/6179426][fix] Exclude UCX tcp transport in disagg unit tests deepseek-v4
#14249 opened May 18, 2026 by Shixiaowei02 Collaborator Loading…
1 task done
@Shixiaowei02
11
[https://nvbugs/5800725][fix] Restore Mistral Large 3 text-only processor
#14248 opened May 18, 2026 by byshiue Collaborator Loading…
@byshiue
4
[None][chore] Update flashinfer-python from 0.6.10 to 0.6.11
#14247 opened May 18, 2026 by lfr-0531 Collaborator Loading…
1 task done
@lfr-0531
5
[TRTLLM-12751][feat] visual-gen /metrics iteration stats producer
#14246 opened May 18, 2026 by JunyiXu-nv Collaborator Loading…
1 task done
@JunyiXu-nv
10
[TRTLLM-12732][fix] Fence V2 KV cache block-offset H2D copy on KV manager stream
#14245 opened May 18, 2026 by Barry-Delaney Collaborator • Draft
@Barry-Delaney
9
[None][refactor] clean up AttentionForwardArgs
#14244 opened May 18, 2026 by yuxianq Collaborator Loading…
1 task done
@yuxianq
6
[None][fix] Update JIT libs using upgraded NVCC version 13.2
#14242 opened May 18, 2026 by heyuhhh Collaborator Loading…
1 task
@heyuhhh
3
[None][perf] DSv4 mem-opts: RoPE cap + MHC pool routing (split from #14053)
#14241 opened May 18, 2026 by lancelly Collaborator • Draft
3 of 4 tasks
@lancelly
ProTip! no:milestone will show everything without a milestone.