Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
226 Open 1,355 Closed
226 Open 1,355 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

Integrate trtllm-gen kernels for QKVGemm, FC13+swiGLU, and FC2 for Llama4
#4201 opened May 10, 2025 by eopXD Loading…
[TRTLLM-5188] fix: [AutoDeploy] update output shape of prepare_fused_mha_metadata_fake
#4199 opened May 9, 2025 by Fridah-nv Loading…
11
Added tests for Llama3.1-70B-BF16 on SM120
#4198 opened May 9, 2025 by farazkh80 • Draft
Extend the Llama-Nemotron-Nano-8B perf-integration-tests
#4195 opened May 9, 2025 by venkywonka Loading…
1
Test main images CI result
#4194 opened May 9, 2025 by ZhanruiSunCh • Draft
@ZhanruiSunCh
5
infra: [TRTLLM-325] Prepare for NGC release - multiplatform build
#4191 opened May 9, 2025 by MartinMarciniszyn Loading…
5
fix: Revert NIXL and ETCD from the main image
#4190 opened May 9, 2025 by Shixiaowei02 Loading…
Cherry-pick feat/llama4's 1-17 commits to main
#4189 opened May 9, 2025 by chenfeiz0326 Loading…
3
[bug/5247505] fix: CP accuracy on Blackwell
#4188 opened May 9, 2025 by DylanChen-NV Loading…
3
infra: open source fmha v2 kernels
#4185 opened May 9, 2025 by qsang-nv Loading…
6
feat: Support for Mistral Small 3.1 24B VLM
#4183 opened May 9, 2025 by brb-nv Loading…
10
^gdr_copy
#4181 opened May 9, 2025 by chuangz0 Loading…
3
add changes for fp8, nemotron-nas, API
#4180 opened May 9, 2025 by shaharmor98 Loading…
12
[TRTQA-2802][fix]: add --host for mgmn serve examples script
#4175 opened May 9, 2025 by xinhe-nv Loading…
Breaking change: perf: Enable scheduling overlap by default
#4174 opened May 9, 2025 by kaiyux Loading…
7
chore: Remove deprecated Python runtime benchmark
#4171 opened May 9, 2025 by kaiyux Loading…
7
exp: pull/4114
#4170 opened May 9, 2025 by tongyuantongyu • Draft
6
[feat] [AutoDeploy] Llama-4 Support
#4163 opened May 8, 2025 by lucaslie Loading…
2 of 5 tasks
@lucaslie
4
[TRTLLM-5054][fix] Removing repeated loading of input processor
#4161 opened May 8, 2025 by rakib-hasan Loading…
3
fix: bump xgrammar
#4160 opened May 8, 2025 by milesial • Draft
3
[nvbugs/5268808][fix] Fix the potential out-of-range-access issue of allreduce workspace.
#4159 opened May 8, 2025 by hyukn • Draft
14
Add test case for kv memory estimation
#4158 opened May 8, 2025 by HuiGao-NV Loading…
@HuiGao-NV
25
[TRTLLM-5050][feat] Enable per-request stats with PyT backend
#4156 opened May 8, 2025 by pcastonguay Loading…
9
Feat: support exporting softmax statistics and update the kernel-selection heuristic
#4155 opened May 8, 2025 by PerkzZheng Loading…
14
remove cache_transceiver_prealloc_size
#4153 opened May 8, 2025 by chuangz0 Loading…
9
ProTip! Updated in the last three days: updated:>2025-05-07.