Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
507 Open 7,100 Closed
507 Open 7,100 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

[TRTLLM-10030][perf] beam search (remove GPU sync + fix batching + refactor)
#11276 opened Feb 4, 2026 by ixlmar • Draft
1 task done
2
[https://nvbugs/5814504][fix] Add skip_pre_hopper flag on NVILA & Nano V2 VLMs
#11275 opened Feb 4, 2026 by yechank-nvidia Loading…
@yechank-nvidia
3
[https://nvbugs/5845769][fix] B300 support on VLMs
#11274 opened Feb 4, 2026 by yechank-nvidia Loading…
@yechank-nvidia
3
[None][feat] Optimize super-v3 nvfp4 for better perf
#11273 opened Feb 4, 2026 by Wanli-Jiang • Draft
1 task done
2
[None][fix] DO NOT REVIEW
#11272 opened Feb 4, 2026 by bo-nv • Draft
1 task
6
[https://nvbugs/5612438][fix] add timeout 14400 for SeedOSS
#11269 opened Feb 4, 2026 by zhhuang-nv Loading…
1 task done
4
AutoDeploy trtllm attention backend with trtllm's kv cache manager direct operation
#11268 opened Feb 4, 2026 by MrGeva Loading…
1 task
@MrGeva
14
[TRTLLM-9771][feat] Make refit compatible with CUDA Graph
#11267 opened Feb 4, 2026 by shuyixiong • Draft
1 task
[https://nvbugs/5848377][fix] fix deepeplowlatency with trtllm moe backend running fp8 DS_R1
#11266 opened Feb 4, 2026 by leslie-fang25 Loading…
1 task done
3
[None][chore] Fix slurm job name
#11265 opened Feb 4, 2026 by yingguo-trt Loading…
1 task done
4
[TRTLLM-10858][feat] Multi-image support for EPD disagg
#11264 opened Feb 4, 2026 by 2ez4bz Loading…
1 task done
1
[None][fix] Fix possible arithmetic overflow in FMHAv2 launcher
#11263 opened Feb 4, 2026 by tongyuantongyu Loading…
1 task done
8
[refactor] Cache CUDA_LAUNCH_BLOCKING with lazy init
#11261 opened Feb 4, 2026 by hnover-nv Loading…
1
[#11234][test] Move test_ad_export_onnx to integration examples
#11260 opened Feb 4, 2026 by nvyocox Loading…
7 tasks done
1
3
[https://nvbugs/5820874][fix] Adjust deepgemm tuning buckets to cover larger num_tokens's scope
#11259 opened Feb 4, 2026 by chenfeiz0326 Loading…
1 task done
@chenfeiz0326
5
[draft] Remove mem est
#11258 opened Feb 4, 2026 by HuiGao-NV • Draft
1 task
8
[None][fix] Fix amax to avoid NaN issue in fp8_blockscale_gemm_kernel.
#11256 opened Feb 4, 2026 by yuxianq Loading…
1 task done
3
[None][chore] Resolve a conflict in the md file
#11255 opened Feb 4, 2026 by ziyixiong-nv Loading…
1 task
5
[None][feat] Enhance support for complex models
#11254 opened Feb 4, 2026 by lowsfer Loading…
@lowsfer
6
[https://nvbugs/5863464][fix] Fix port binding conflict in disagg benchmarking script
#11253 opened Feb 4, 2026 by brb-nv Loading…
1 task done
5
[https://nvbugs/5863443][fix] Fix message truncation in Helix CP cache transmission
#11252 opened Feb 4, 2026 by brb-nv Loading…
1 task done
4
[None][infra] Use frontend dgx-h100 and b200 slurm platforms
#11251 opened Feb 4, 2026 by mlefeb01 Loading…
1 task
@mlefeb01
4
[DRAFT][#11203][feat] Optimize weight shape extraction
#11250 opened Feb 4, 2026 by taylor-yb-lee • Draft
1 task
[https://nvbugs/5800679][fix] Re-enable test after bug fixed
#11249 opened Feb 4, 2026 by dongfengy Loading…
1 task done
@dongfengy
7
[https://nvbugs/5849697][fix] Refine QA Test List for SM120
#11248 opened Feb 4, 2026 by dongfengy Loading…
1 task done
@dongfengy
7
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.