Skip to content

Issues: NVIDIA/TensorRT-LLM

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

429 Open 1,852 Closed
429 Open 1,852 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

Qwen 32B becomes 8x slower when enabling lora bug Something isn't working
#2883 opened Mar 13, 2025 by ShuaiShao93
4 tasks
gemma 3 architecture
#2880 opened Mar 12, 2025 by Alireza3242
1
The lookahead speculative decoding failed when applied to gpt2 0.1b.
#2879 opened Mar 12, 2025 by JeRainXiong
TensorRT-LLM for MiniCPM-V2.6
#2878 opened Mar 12, 2025 by Single430
Codestral-22B not support FP8?
#2874 opened Mar 11, 2025 by activezhao
2
Custom sampler for executor API
#2871 opened Mar 10, 2025 by maxilevi
DeepSeek R1 tensorrt workflow
#2870 opened Mar 10, 2025 by akhoroshev
3
an illegal memory access was encountered with python benchmark. bug Something isn't working Investigating
#2868 opened Mar 10, 2025 by yuqie
1 of 4 tasks
2
internvl2.5
#2867 opened Mar 10, 2025 by ChenJian7578
1
Could not run on a machine with dual RTX 5090s, using WSL2 and Docker bug Something isn't working Investigating triaged Issue has been triaged by maintainers
#2864 opened Mar 7, 2025 by shahizat
4 tasks
8
Could Not Run Deepseek-R1 Engine with Nvidia Triton Server in 8xH200 triaged Issue has been triaged by maintainers
#2863 opened Mar 7, 2025 by Bihan
2
Does TensorRT-LLm have a roadmap for techniques like Deepseek's EPLB, DeepGEMM, FlashMLA, DeepEP?
#2861 opened Mar 6, 2025 by dongs0104
TensorRT-LLM for Qwen2.5-VL triaged Issue has been triaged by maintainers
#2859 opened Mar 6, 2025 by ananthakrishnanpv01
Getting runtime error OOM for generation logits and never go back to normal Investigating triaged Issue has been triaged by maintainers waiting for feedback
#2857 opened Mar 5, 2025 by tlyhenry
7
Cannot build engine w. FP8 FMHA on Blackwell Investigating triaged Issue has been triaged by maintainers
#2855 opened Mar 5, 2025 by indra83
5
Fail to convert InternVL2-1B model in container bug Something isn't working triaged Issue has been triaged by maintainers
#2854 opened Mar 5, 2025 by tjliupeng
1 of 4 tasks
1
TensorRT-LLM 0.17.0.post1 fails to run Whisper on 5080 GPU bug Something isn't working Investigating triaged Issue has been triaged by maintainers
#2847 opened Mar 3, 2025 by Banner-Wang
4 tasks
4
[Error] TypeError: LlmArgs.__init__() got an unexpected keyword argument 'enable_attention_dp' Investigating triaged Issue has been triaged by maintainers
#2846 opened Mar 3, 2025 by tingjun-cs
【Error】ValueError: Unknown architecture for AutoModelForCausalLM: DeepseekV3ForCausalLM triaged Issue has been triaged by maintainers
#2845 opened Mar 3, 2025 by tingjun-cs
2
Inquiry on 0.18 Release plan and R1 TRT engine support in different branch triaged Issue has been triaged by maintainers
#2844 opened Mar 3, 2025 by junliu-mde
7
tensorrt_llm_ucx_wrapper.dll and tensorrt_llm_ucx_wrapper.lib does not exist triaged Issue has been triaged by maintainers
#2834 opened Feb 28, 2025 by LRLVEC
1
RoBERTa model conversion does not pass the huggingface test bug Something isn't working Investigating triaged Issue has been triaged by maintainers
#2829 opened Feb 26, 2025 by arinaruck
2 of 4 tasks
4
Bottleneck in _initialize_and_fill_output func. in multimodal_runner_cpp.py Investigating triaged Issue has been triaged by maintainers
#2827 opened Feb 26, 2025 by nicekevin
1
pytorch backend run error with fp8 hf model bug Something isn't working triaged Issue has been triaged by maintainers waiting for feedback
#2825 opened Feb 26, 2025 by nickole2018
2 of 4 tasks
1
Baichuan2 model core dumped when running after quantization to FP8 bug Something isn't working Investigating triaged Issue has been triaged by maintainers
#2824 opened Feb 26, 2025 by kanebay
2 of 4 tasks
ProTip! Follow long discussions with comments:>50.