Skip to content

Issues: NVIDIA/TensorRT-LLM

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

567 Open 1,912 Closed
567 Open 1,912 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Call for contributions]The development plan of large-scale EP support in TensorRT-LLM Community Engagement
#4127 opened May 7, 2025 by juney-nvidia
1
Qwen2-0.5B Inference Freezes with TensorRT-LLM on RTX 5000
#4118 opened May 7, 2025 by ashkanzarkhah
Install from docs not working bug Something isn't working Installation triaged Issue has been triaged by maintainers
#4099 opened May 6, 2025 by darraghdog
4 tasks
@syuoni
5
convert_checkpoint.py with Llama 4 ?
#4088 opened May 6, 2025 by LRUnivAlban
apply_per_channel_scale may fail to launch when the input sequence length is extremely large bug Something isn't working
#4085 opened May 6, 2025 by StudyingShao
1 of 4 tasks
@StudyingShao
1
deepseek-fp4 quality issue -- bad generation output after the second batch run
#4072 opened May 5, 2025 by xwuShirley
2
Use report.json from trtllm-bench in perf integration tests instead of redirecting stdout others
#4071 opened May 5, 2025 by venkywonka
1
LLama 3.1 405B FP8 perf low on B200 bug Something isn't working
#4043 opened May 3, 2025 by andyluo7
4 tasks
Deepseek R1 and V3, FP4 quant, output quality issues at batch size > 2 bug Something isn't working triaged Issue has been triaged by maintainers
#4037 opened May 2, 2025 by pankajroark
2 of 4 tasks
@litaotju @Tracin @juney-nvidia
6
Add FP8 Support for Llama-4-Maverick on B200 (Feature Request)
#4033 opened May 2, 2025 by indianspeedster
Is text-only inference supported for multi-modal vision models like Llama 3.2 11b/90b Vision Instruct?
#4012 opened May 1, 2025 by natehofmann
[bug] Lookahead spec-dec verifies w guesses instead of g bug Something isn't working
#4003 opened Apr 30, 2025 by mahmoudhas
3 of 4 tasks
Front page readme should list models supported.
#3995 opened Apr 30, 2025 by NikolaBorisov
Qserve-w4a8 Shows Lower Computational Efficiency on H20 not a bug Some known limitation, but not a bug.
#3977 opened Apr 30, 2025 by StaryDing
2 of 4 tasks
2
SW Architecture Enhancements roadmap SW Architecture
#3966 opened Apr 29, 2025 by mk-nvidia
Reasoning-related enhancements feature request New feature or request roadmap
#3965 opened Apr 29, 2025 by mk-nvidia
1.0 Architecture roadmap SW Architecture
#3964 opened Apr 29, 2025 by mk-nvidia
Disaggregated Prefill & Decode serving optimizations Investigating Performance Issue about performance number roadmap triaged Issue has been triaged by maintainers
#3963 opened Apr 29, 2025 by mk-nvidia
MoE optimizations Investigating Performance Issue about performance number roadmap triaged Issue has been triaged by maintainers
#3962 opened Apr 29, 2025 by mk-nvidia
Support versioned github.io doc to make it easy to map code with the corresponding doc version Documentation Improvements or additions to documentation Investigating roadmap triaged Issue has been triaged by maintainers
#3961 opened Apr 29, 2025 by mk-nvidia
Re-organize the example directory into Feature level examples and Model level examples Documentation Improvements or additions to documentation Investigating roadmap triaged Issue has been triaged by maintainers
#3960 opened Apr 29, 2025 by mk-nvidia
Publication of pre-built development and deployment Docker containers to improve TensorRT-LLM user experience Ease of Use roadmap
#3959 opened Apr 29, 2025 by mk-nvidia
Intra-1.x-version backward compatibility for selected APIs. Investigating roadmap triaged Issue has been triaged by maintainers
#3958 opened Apr 29, 2025 by mk-nvidia
Plenty of regressions in trt-llm v0.20.0 bug Something isn't working
#3955 opened Apr 29, 2025 by michaelfeil
4 tasks
1
Context node crash when using PD Disaggregation bug Something isn't working
#3937 opened Apr 29, 2025 by nsealati
2 of 4 tasks
ProTip! Updated in the last three days: updated:>2025-05-04.