Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
437 Open 5,529 Closed
437 Open 5,529 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-909][feat] Overlap context chunks in pipeline parallel mode
#9308 opened Nov 19, 2025 by Funatiq • Draft
1 task
2
fix mtp.py typo Community want to contribute PRs initiated from Community
#9307 opened Nov 19, 2025 by attack204 Loading…
1 task
1
[TRTLLM-9295][fix] use greedy decoding in test_openai_compatible_json_schema
#9305 opened Nov 19, 2025 by ixlmar Loading…
1 task done
6
[None][infra] Enable single-gpu CI on spark
#9304 opened Nov 19, 2025 by EmmaQiaoCh • Draft
1 task done
4
[TRTLLM-9160][doc] add doc to llm_runtime.py
#9303 opened Nov 19, 2025 by Superjomn Loading…
1 task done
7
[None][feat] Add processed logprobs
#9302 opened Nov 19, 2025 by dominicshanshan • Draft
1 task done
12
[#9198][feat] Refactor dist ops in AutoDeploy
#9301 opened Nov 19, 2025 by MrGeva Loading…
1 task done
9
[https://nvbugs/5667687][fix] Set correct lm_head_tp_size_upper_bound
#9300 opened Nov 19, 2025 by lancelly Loading…
9
support for newer checkpoints Community want to contribute PRs initiated from Community
#9299 opened Nov 19, 2025 by binghanc • Draft
[None][feat] Support custom chat template for tool calling
#9297 opened Nov 19, 2025 by LinPoly Loading…
1 task done
@LinPoly
10
[https://nvbugs/5629833][fix] Don't fill tensors
#9296 opened Nov 19, 2025 by HuiGao-NV Loading…
1 task
4
[https://nvbugs/5625990][fix] Fix block copy from GPU to GPU for partial reuse in the KV cache manager KV-Cache Management kv-cache management for efficient LLM inference
#9295 opened Nov 19, 2025 by eopXD • Draft
1 task done
@eopXD
7
[None][fix] Replace PYTORCH_CUDA_ALLOC_CONF with PYTORCH_ALLOC_CONF to fix deprecation warning
#9294 opened Nov 19, 2025 by jiaganc Loading…
1 task
1
[None][infra] Modify SBSA build thread from 4 to 8
#9293 opened Nov 19, 2025 by ZhanruiSunCh Loading…
1 task done
7
[TRTLLM-9086][doc] Clean up TODOs in documentation
#9292 opened Nov 19, 2025 by QiJune Loading…
1 task done
2
[None][infra] Fix OpenSearchDB env
#9291 opened Nov 19, 2025 by ZhanruiSunCh • Draft
1 task
11
[None][infra] Add fallback when get wheel from build stage is fail
#9290 opened Nov 19, 2025 by ZhanruiSunCh Loading…
1 task
9
[TRTLLM-9370][feat] Integration of CuteDSL NVFP4 grouped GEMM (Part 2: SwiGLU Fusion and Finalize Fusion)
#9288 opened Nov 19, 2025 by syuoni Loading…
1 task done
@syuoni
4
[TRI-332] [fix] Fix L0_backend_trtllm Community want to contribute PRs initiated from Community
#9282 opened Nov 18, 2025 by yinggeh Loading…
1 task done
4
[https://nvbugs/5508267][fix] Proper handling of inactive canceled requests
#9280 opened Nov 18, 2025 by thorjohnsen Loading…
1 task done
@thorjohnsen
4
[#9237][feat]: enable iter stats in autodeploy
#9278 opened Nov 18, 2025 by NVShreyas Loading…
1 task done
1
9
[#9147][feat] AutoDeploy: Draft Target Speculative Decoding
#9275 opened Nov 18, 2025 by govind-ramnarayan Loading…
1 task done
1
43
Draft: [TRTC-1934][feat] Initial SA recipe database.
#9272 opened Nov 18, 2025 by FrankD412 Loading…
1 task done
@FrankD412
19
[TRTLLM-9295][test] enable FlashInfer.sampling by default (DO NOT MERGE)
#9270 opened Nov 18, 2025 by ixlmar • Draft
1 task
15
[TRTLLM-9191][feat] support out-of-tree models in trtllm-serve
#9269 opened Nov 18, 2025 by ixlmar Loading…
1 task done
13
ProTip! Type g i on any issue or pull request to go back to the issue listing page.