Skip to content

Pull requests: nv-auto-deploy/TensorRT-LLM

New pull request New
31 Open 213 Closed
31 Open 213 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][feat] Add AutoDeploy custom model for GLM-5 (glm_moe_dsa)
#246 opened Mar 13, 2026 by suyoggupta Loading…
@suyoggupta
1
[None][feat] Add Gemma3n model + Shared-kv attention support in AutoDeploy
#244 opened Mar 13, 2026 by bmarimuthu-nv Loading…
@bmarimuthu-nv
27
[None][feat] Add AD custom model for MiMo-V2-Flash
#239 opened Mar 12, 2026 by lucaslie • Draft
5 tasks done
@lucaslie
9
[None][feat] AutoDeploy: update the test list
#236 opened Mar 12, 2026 by nvchenghaoz Loading…
1 task
@nvchenghaoz
[None][feat] Add AD custom model for DeepSeek-V3.2 family
#232 opened Mar 12, 2026 by lucaslie • Draft
@lucaslie
7
[None][revert] Revert "Add AutoDeploy custom model for Starcoder2 (#2…
#217 opened Mar 12, 2026 by govind-ramnarayan • Draft
1 task
@govind-ramnarayan
[None][feat] AutoDeploy: add support for mixtral/pixtral
#212 opened Mar 11, 2026 by nvchenghaoz Loading…
1 task
@nvchenghaoz
[None][feat] Add AD custom models for Jamba (Mamba v1 + Attention hybrid)
#200 opened Mar 11, 2026 by govind-ramnarayan Loading…
5 tasks
@govind-ramnarayan
25
[AutoDeploy] onboarding allenai/OLMo-2-0325-32B-DPO
#186 opened Mar 10, 2026 by taylor-yb-lee Loading…
1 task
@taylor-yb-lee
1
[None][bug] Qwen3.5 image fix
#179 opened Mar 3, 2026 by bmarimuthu-nv Loading…
1 task
Gramnarayan/load superv3 mtp head rebased
#178 opened Feb 26, 2026 by govind-ramnarayan • Draft
1 task
[TRTLLM-11567][feat] Manual config sharding support for Gated DeltaNet layer
#175 opened Feb 19, 2026 by greg-kwasniewski1 Loading…
1 task done
qwen3.5 perf tuning
#174 opened Feb 18, 2026 by suyoggupta Loading…
1 task
Add fused Triton MoE routing kernel with pattern matcher transform
#173 opened Feb 17, 2026 by suyoggupta Loading…
1 task
[TRTLLM-11486][feat] GatedDeltaNet sharding
#171 opened Feb 12, 2026 by greg-kwasniewski1 Loading…
1 task done
Optimize MOE export by tracing with reduced experts and expanding graph
#170 opened Feb 11, 2026 by suyoggupta • Draft
1 task
Spec Dec: Fix Overlap Scheduler Garbage Output
#168 opened Feb 1, 2026 by govind-ramnarayan • Draft
1 task done
4
Sg/multi stream tp
#166 opened Jan 20, 2026 by suyoggupta Loading…
1 task
Fix TRTLLM moe nvfp4 for nano
#164 opened Jan 15, 2026 by nvchenghaoz Loading…
weight cast
#162 opened Nov 26, 2025 by suyoggupta Loading…
1 task
Fix the unit test errors / enable accuracy tests
#150 opened Oct 1, 2025 by nvchenghaoz Loading…
8
Sg/bamba bench
#139 opened Sep 24, 2025 by suyoggupta • Draft
2
Support Pixtral
#128 opened Aug 14, 2025 by nvchenghaoz • Draft
Support Qwen 2.5 VL
#127 opened Aug 12, 2025 by nvchenghaoz • Draft
4
Skip pattern matching in specified modules
#125 opened Aug 8, 2025 by suyoggupta • Draft
ProTip! Mix and match filters to narrow down what you’re looking for.