Pull requests: NVIDIA/TensorRT-LLM
Pull requests list
[None][fix] Size seq-slot pool to cover disagg-gen KV admission to mitigate hangs
#18983
opened Sep 9, 2026 by
brb-nv
Collaborator
Loading…
1 task done
[TRTLLMINF-368][infra] update cluster config for OCI-JHB
#18982
opened Sep 9, 2026 by
tburt-nv
Collaborator
Loading…
1 task done
[https://nvbugs/6670516][fix] Call build_kv_page_indices with current signature
#18980
opened Sep 9, 2026 by
brb-nv
Collaborator
Loading…
1 task done
[https://nvbugs/5836830][test] Remove DeepSeek-R1 W4AFP8 8-GPU quickstart test from QA list
#18979
opened Sep 9, 2026 by
brnguyen2
Collaborator
Loading…
[None][fix] compose telemetry capture policies
api-compatible
Accepted LLM API contract change that is backwards-compatible
#18978
opened Sep 9, 2026 by
Mgluhovskoi
Collaborator
Loading…
[None][fix] Size the FlashInfer page-index buffer for VSWA on V1 KV cache
#18975
opened Sep 9, 2026 by
brnguyen2
Collaborator
Loading…
1 task done
[None][fix] Restore SM107 2x-mmaK acceptance and fine-grained sync PDL path
#18974
opened Sep 9, 2026 by
farazkh80
Collaborator
Loading…
[None][fix] Stabilize MoE LoRA CUDA graph scratch
#18972
opened Sep 9, 2026 by
achartier
Collaborator
Loading…
1 task done
[#18849][fix] Pass vocab_size to hybrid-Mamba KV cache managers
#18970
opened Sep 9, 2026 by
dibyo10
Loading…
1 task done
[None][docs] drop deleted accuracy_eval/gen_server_config from disagg benchmark README
#18969
opened Sep 9, 2026 by
imitater-dou
Loading…
[None][docs] fix multimodal serve client path, base64 util, and bench doc link
#18967
opened Sep 9, 2026 by
imitater-dou
Loading…
4 tasks
[None][docs] fix visual_gen README cosmos3 and qwen-edit example paths
ci: full pre-merge approved
VisualGen
#18966
opened Sep 9, 2026 by
imitater-dou
Loading…
[None][docs] fix VisualGen NVL72 config .yml → .yaml in blog25
#18965
opened Sep 9, 2026 by
imitater-dou
Loading…
2 tasks
[None][fix] correct disagg_utils __all__ entry to extract_disagg_cfg
#18963
opened Sep 9, 2026 by
Anai-Guo
Loading…
[None][docs] retarget moved performance doc URLs in tech blogs
#18962
opened Sep 9, 2026 by
imitater-dou
Loading…
3 tasks done
[None][docs] drop ghost enable_overlap_scheduler from trtllm-serve Slurm example
#18961
opened Sep 9, 2026 by
imitater-dou
Loading…
3 tasks done
[None][docs] retarget ModelOpt llm_ptq docs paths to hf_ptq
#18960
opened Sep 9, 2026 by
imitater-dou
Loading…
2 tasks done
[None][docs] drop deleted lm_eval_ad.py from auto_deploy README
#18959
opened Sep 9, 2026 by
imitater-dou
Loading…
2 of 3 tasks
[https://nvbugs/6739081][fix] Preserve per-layer KV page addressing for mixed head sizes
#18957
opened Sep 9, 2026 by
yuxianq
Collaborator
Loading…
1 task done
[None][docs] retarget ModelOpt examples llm_ptq paths to hf_ptq
#18956
opened Sep 9, 2026 by
imitater-dou
Loading…
3 tasks done
[None][docs] fix dead example links in legacy speculative-decoding
#18955
opened Sep 9, 2026 by
imitater-dou
Loading…
4 tasks done
[None][fix] Match layer-wise benchmark V2 pool sizing to dummy request lengths
api-compatible
Accepted LLM API contract change that is backwards-compatible
#18954
opened Sep 9, 2026 by
yizhang-nv
Member
Loading…
1 task done
ProTip!
Filter pull requests by the default branch with base:main.