Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
363 Open 3,302 Closed
363 Open 3,302 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

Draft: Split atten_metadata
#6638 opened Aug 5, 2025 by nvkgoyal • Draft
11
Update README.md
#6636 opened Aug 5, 2025 by esnvidia Loading…
4
[None][ci] move unittests to sub-directories
#6635 opened Aug 5, 2025 by Funatiq • Draft
8
[#5048][AutoDeploy: Optimize prepare_inputs
#6634 opened Aug 5, 2025 by galagam • Draft
2
[feat] move kv cache measure into transfer session
#6633 opened Aug 5, 2025 by zhengd-nv Loading…
4
test: align kv_frac in perf test with perflab and add more cases for 4 gpus GB200
#6632 opened Aug 5, 2025 by ruodil Loading…
4
[https://nvbugs/5436461][infra] Adjust free_gpu_memory_fraction of test_eagle3 to prevent OOM on CI
#6631 opened Aug 5, 2025 by leslie-fang25 Loading…
4
[TRTLLM-5863][feat] Support MoE INT8 Weight-Only-Quantization in PyTorch Workflow
#6629 opened Aug 5, 2025 by Yuening-wa Loading…
3
[TRTLLM-6637][feat] Resolve KV cache divergence issue
#6628 opened Aug 5, 2025 by ziyixiong-nv Loading…
4
[None][fix] Fix unnecessary GPU synchronization in torch sampler caused by incorrect tensor reference Community want to contribute PRs initiated from Community
#6626 opened Aug 5, 2025 by zhanghaotong Loading…
2
[feat] add LayerNorm module
#6625 opened Aug 5, 2025 by Funatiq Loading…
8
[None][perf] Improve the performance of online EPLB on Hopper by better overlapping
#6624 opened Aug 5, 2025 by jinyangyuan-nvidia Loading…
@jinyangyuan-nvidia
17
[TRTLLM-6675][infra] Nixl test completion
#6623 opened Aug 5, 2025 by bo-nv Loading…
12
[TRTLLM-6772][feat] Multimodal benchmark_serving support
#6622 opened Aug 5, 2025 by yechank-nvidia Loading…
@yechank-nvidia
10
[None][Doc] Add doc for multimodal feature support matrix
#6619 opened Aug 5, 2025 by chang-l Loading…
5
[TRTLLM-6898][feat] make fused_moe_cute_dsl work on blackwell
#6616 opened Aug 5, 2025 by limin2021 Loading…
8
refactor: Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic
#6615 opened Aug 5, 2025 by yizhang-nv Loading…
7
[None][fix] Adjust default moe_max_num_tokens to fix OOM.
#6614 opened Aug 5, 2025 by yuxianq Loading…
4
[TRTLLM-5252][fix] Propagate mapping to intermediate layers
#6611 opened Aug 4, 2025 by 2ez4bz • Draft
9
[None][doc] Created Deployment Guide for SGLang DeepSeek-R1 FP8 and NVFP4 Community want to contribute PRs initiated from Community
#6610 opened Aug 4, 2025 by jamieliNVIDIA Loading…
13
Update CMakeLists.txt extend find_library names Community want to contribute PRs initiated from Community
#6609 opened Aug 4, 2025 by mc-nv Loading…
4
feat: Enable nanobind as the default binding library
#6608 opened Aug 4, 2025 by Linda-Stadter • Draft
5
[TRTLLM-5633][infra] Change the TOT repo to default-llm-repo for merge waive list
#6605 opened Aug 4, 2025 by yiqingy0 Loading…
6
[None][chore] Enhance trtllm-serve example test
#6604 opened Aug 4, 2025 by LinPoly Loading…
9
[TRTLLM-6092][doc] Add LoRA feature usage doc
#6603 opened Aug 4, 2025 by shaharmor98 Loading…
5
ProTip! Mix and match filters to narrow down what you’re looking for.