-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Pull requests: NVIDIA/TensorRT-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: add heuristics for checkpoint files prefetching.
#4765
opened May 29, 2025 by
yuxianq
Loading…
infra: upload imageTag info to artifactory and add ngc_staging to sav…
#4764
opened May 29, 2025 by
ZhanruiSunCh
Loading…
Draft: feat: port MakeDecodingBatchInputOutput alg to python
#4761
opened May 29, 2025 by
dcampora
Loading…
fix: [nvbugs/5310520] disable embed_tokens's TP when DP enabled for llama model.
#4758
opened May 29, 2025 by
yuxianq
Loading…
[TRTLLM-3927] [feat] Finalize + Allreduce + add + rmsnorm fusion
#4756
opened May 29, 2025 by
zongfeijing
•
Draft
tests: [TRTQA-2905] improve timeout report for qa test cases
#4753
opened May 29, 2025 by
crazydemo
Loading…
feat: cache reuse support (selective cache transfer) in mla cache formatter
#4749
opened May 29, 2025 by
zhengd-nv
Loading…
[nvbugs/5302709] fix: Use HF vision tower for llava-next on A100
#4747
opened May 29, 2025 by
amukkara
Loading…
[nvbugs/5297821] Fix llama4 disaggregated serving accuracy tests
#4743
opened May 28, 2025 by
Tabrizian
Loading…
fix: Skip torch distributed training for dummy heads creation
#4742
opened May 28, 2025 by
brb-nv
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.