Skip to content

Pull requests: NVIDIA/TensorRT-LLM

New pull request New
233 Open 1,526 Closed
233 Open 1,526 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

test: [CI] Add failed cases into waives.txt
#4429 opened May 19, 2025 by xinhe-nv Loading…
fix[nvbug/5286515]: trtllm-llmapi-launch on single node single gpu
#4428 opened May 19, 2025 by Superjomn Loading…
2
draft: [Auto Deploy] Deepseek support for MLA attention with compressed kv
#4427 opened May 19, 2025 by sugunav14 Loading…
1 of 3 tasks
Update "Roadmap" link under README.md to the issues with Roadmap label
#4425 opened May 19, 2025 by AdamzNV Loading…
[nvbug/5028235][fix]pytest bindings tokens logtis comparison.
#4424 opened May 19, 2025 by dominicshanshan Loading…
5
[DON'T MERGER] Sharing only: Add quickstart dataset
#4423 opened May 19, 2025 by SimengLiu-nv • Draft
fix gemma2 27b fp8
#4418 opened May 18, 2025 by netanel-haber • Draft
3
test: [CI] remove closed bugs
#4417 opened May 18, 2025 by xinhe-nv Loading…
3
[feat] Multi-block mode for Hopper spec dec XQA kernel
#4416 opened May 18, 2025 by jhaotingc Loading…
26
[TRTLLM-4932] Add CLI accuracy tests for Phi-4-mini-instruct
#4415 opened May 18, 2025 by moraxu Loading…
6
[Fix][Deepseek] Fix bugs in TestDeepSeekR1
#4413 opened May 18, 2025 by hlu1 Loading…
Scaffoldingllm supports MCP Community Engagement Community want to contribute
#4410 opened May 17, 2025 by wu1du2 Loading…
6
test(perf): Extend the Llama-Nemotron-Nano-8B perf-integration-tests (pyt)
#4407 opened May 16, 2025 by venkywonka • Draft
Add pytorch backend team
#4405 opened May 16, 2025 by kevinch-nv Loading…
[nvbug/5285881][fix] Fix chunked prefill + overlap scheduler
#4402 opened May 16, 2025 by mikeiovine Loading…
4
feature: align sample state with trtllm sampler sample state
#4401 opened May 16, 2025 by netanel-haber • Draft
doc: [TRTLLM-325]Integrate the NGC image in Makefile automation and document
#4400 opened May 16, 2025 by MartinMarciniszyn Loading…
@MartinMarciniszyn
7
fix: [nvbugs/5287097] Align PP layer distribution between pytorch and TRT flow.
#4399 opened May 16, 2025 by yuxianq Loading…
25
refactor: DisaggExecutorTest
#4398 opened May 16, 2025 by Funatiq • Draft
4
Feat: add chunked-attention kernels on Blackwell
#4394 opened May 16, 2025 by PerkzZheng Loading…
@PerkzZheng
14
tests: add llama 3.3 70b 2 nodes tests
#4391 opened May 16, 2025 by xinhe-nv • Draft
Add bot option to show detailed logs
#4390 opened May 16, 2025 by yiqingy0 Loading…
2
[TRTLLM-4932] Add CLI accuracy tests for Llama-4-Maverick-17B-128E-Instruct and LLM API FP8 variant
#4389 opened May 16, 2025 by moraxu • Draft
3
[TRTLLM-4932] Add CLI accuracy tests for Llama-4-Scout-17B-16E-Instruct
#4388 opened May 16, 2025 by moraxu • Draft
3
feat: large-scale EP(part 2: MoE Load Balancer - core utilities)
#4384 opened May 16, 2025 by dongxuy04 • Draft
6
ProTip! Follow long discussions with comments:>50.