Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
185 Open 901 Closed
185 Open 901 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Draft: test: [CI] Add failed cases into waives.txt
#3627 opened Apr 16, 2025 by xinhe-nv • Draft
chore: Use ellipsis as default value to detect whether residual argument is provided
#3626 opened Apr 16, 2025 by yuxianq Loading…
2
feat: Overlap scheduling in C++ runtime
#3625 opened Apr 16, 2025 by Funatiq • Draft
5
Fix [NVBUG 5219533 5220758] Fix script options for engines.
#3622 opened Apr 16, 2025 by Tracin Loading…
3
Fix: [NVBUG 5201530]Fix merge dummy request when DP + Overlap + Cuda graph.
#3621 opened Apr 16, 2025 by Tracin Loading…
2
tests: change qa perf test to trtllm-bench
#3619 opened Apr 16, 2025 by ruodil Loading…
[Draft]test: add INTEGRATION_TEST env var to speed up integration test
#3618 opened Apr 16, 2025 by crazydemo Loading…
chore: Add etcd docker dependency
#3616 opened Apr 16, 2025 by Shunkangz Loading…
Updating the run.py to make the draft target model run with the LLaMa 3 1B/8B
#3615 opened Apr 16, 2025 by mayani-nv Loading…
disable ib for ucx test
#3613 opened Apr 16, 2025 by chuangz0 Loading…
3
feat: Support unfused rope in MLA.
#3610 opened Apr 16, 2025 by yuxianq Loading…
5
feat: Add support for smaller hidden_dim in AR fusion kernel
#3609 opened Apr 16, 2025 by yilin-void Loading…
@yilin-void
6
feat: Add Dynasor-CoT in scaffolding examples
#3605 opened Apr 16, 2025 by GindaChen • Draft
test: add kv cache event tests for disagg workers
#3602 opened Apr 16, 2025 by zhengd-nv Loading…
8
fix: fix cublas_scaled_mm
#3600 opened Apr 16, 2025 by dc3671 • Draft
22
test: add multinode test case for deepseek-v3
#3599 opened Apr 16, 2025 by crazydemo Loading…
feat: add etcd dependency and interface
#3597 opened Apr 16, 2025 by Shunkangz Loading…
@Shunkangz
4
test: add quickstart test for nemotron-ultra
#3596 opened Apr 16, 2025 by crazydemo Loading…
test:restore fp8 kv cache testing for L0
#3595 opened Apr 16, 2025 by nv-guomingz Loading…
@litaotju
6
test: Get Eagle tests working
#3593 opened Apr 16, 2025 by brb-nv Loading…
3
feat: trtllm-serve multimodal support
#3590 opened Apr 16, 2025 by yechank-nvidia Loading…
13
feat: [AutoDeploy] generalizing cudagraph to multiple dynamic inputs
#3589 opened Apr 16, 2025 by lucaslie Loading…
@lucaslie
4
feat: Disaggregated router class
#3584 opened Apr 15, 2025 by pcastonguay Loading…
18
feat: Integrate GPUDirect Storage (GDS) into Executor API
#3582 opened Apr 15, 2025 by DomBrown Loading…
@DomBrown
11
fix : release torch-managed memory as soon as it's not needed
#3579 opened Apr 15, 2025 by peaceh-nv Loading…
3
ProTip! Adding no:label will show everything without a label.