Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
372 Open 3,196 Closed
372 Open 3,196 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

doc: Add Paged Attention, IFB, and Request Scheduling page
#6532 opened Aug 1, 2025 by kaiyux Loading…
1
[https://nvbugs/5423962][fix] Fix broken links
#6531 opened Jul 31, 2025 by chenopis Loading…
@chenopis
2
doc:[AutoDeploy]: Move AutoDeploy README.md to torch docs
#6528 opened Jul 31, 2025 by Fridah-nv Loading…
@Fridah-nv
13
fix: serialize the window_size in the kv event Community want to contribute PRs initiated from Community
#6526 opened Jul 31, 2025 by richardhuo-nv Loading…
6
refactor: Simplify finish reasons handling in DecoderState
#6524 opened Jul 31, 2025 by Funatiq • Draft
5
fix: correct scaling factor calculation in tests/unittest/trt/functional/test_fp4_gemm.py Community want to contribute PRs initiated from Community
#6523 opened Jul 31, 2025 by muse-coder Loading…
1
[6826][feat] Allow sending more than 2GiB through MPI by using mpi4py.util.pkl5
#6522 opened Jul 31, 2025 by amitz-nv • Draft
1
Remove expand configuration from mamba2 mixer
#6521 opened Jul 31, 2025 by danielafrimi Loading…
@danielafrimi
5
[AutoDeploy] merge feat/ad-2025-07-22
#6520 opened Jul 31, 2025 by lucaslie Loading…
16
[None][infra] Pin the version for triton to 3.3.1 (#6508)
#6519 opened Jul 31, 2025 by chzblych Loading…
7
[TRTLLM-4279] fix: Add a protection test for checking trtllm custom ops
#6515 opened Jul 31, 2025 by yali-arch Loading…
9
add cute dsl deepgemm fp8 blowise op
#6514 opened Jul 31, 2025 by limin2021 Loading…
4
refactor: Return the first token ahead of time
#6512 opened Jul 31, 2025 by Shixiaowei02 Loading…
@Tabrizian
6
chore: Make example SLURM scripts more parameterized
#6511 opened Jul 31, 2025 by kaiyux Loading…
10
[6683][feat] Support LoRA reload CPU cache evicted adapter
#6510 opened Jul 31, 2025 by amitz-nv Loading…
@amitz-nv
19
[Draft - WIP] Upgrade dependencies version to avoid security vulnerability
#6506 opened Jul 31, 2025 by yibinl-nvidia • Draft
7
[https://nvbugspro.nvidia.com/bug/5412562] Allocate MoE workspace only when necessary
#6502 opened Jul 31, 2025 by nv-yilinf Loading…
9
fix: Update cuda memory alignment as 256 to match cublas12.9.1
#6501 opened Jul 31, 2025 by Wanli-Jiang • Draft
9
Feat/mtp opt 2 lamport allgather
#6500 opened Jul 31, 2025 by ameynaik-hub Loading…
@yilin-void @hyukn
@hello-11 @Kefeng-Duan @ameynaik-hub
9
[fix] Fix DeepSeek w4a8 weight loading
#6498 opened Jul 31, 2025 by jinyangyuan-nvidia Loading…
@jinyangyuan-nvidia
12
Refactoring input prep to allow out-of-tree models
#6497 opened Jul 31, 2025 by rakib-hasan • Draft
41
feat: Add support for fused gate_up_proj scales for FP8 blockwise
#6496 opened Jul 30, 2025 by achartier Loading…
5
Update Documentation link to point to docs instead of docs source code Community want to contribute PRs initiated from Community
#6495 opened Jul 30, 2025 by asrivas Loading…
2
[TRTLLM-6812][feat] Add standardized GitHub issue templates and disable blank issues
#6494 opened Jul 30, 2025 by venkywonka Loading…
@venkywonka
10
[feat] add support for Eclairv2 model - cherry-pick changes
#6493 opened Jul 30, 2025 by yibinl-nvidia Loading…
@yibinl-nvidia
21
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.