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

419 Open 1,831 Closed
419 Open 1,831 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

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
Feature Request: Update xgrammar Library
#2832 opened Feb 27, 2025 by jellysnack
@syuoni
DeepSeek v3 support through old (non pytorch) workflow
#2831 opened Feb 27, 2025 by ttim
2
RoBERTa model conversion does not pass the huggingface test bug Something isn't working
#2829 opened Feb 26, 2025 by arinaruck
2 of 4 tasks
1
Bottleneck in _initialize_and_fill_output func. in multimodal_runner_cpp.py
#2827 opened Feb 26, 2025 by nicekevin
Fail to build Tensorrt-LLM, error related to build ucxx bug Something isn't working triaged Issue has been triaged by maintainers
#2826 opened Feb 26, 2025 by tjliupeng
4 tasks
1
pytorch backend run error with fp8 hf model bug Something isn't working
#2825 opened Feb 26, 2025 by nickole2018
2 of 4 tasks
Baichuan2 model core dumped when running after quantization to FP8 bug Something isn't working
#2824 opened Feb 26, 2025 by kanebay
2 of 4 tasks
Accuracy issue with R1 FP4 checkpoint
#2822 opened Feb 25, 2025 by laikhtewari
1
Qwen 2.5 FP8?
#2819 opened Feb 25, 2025 by jolyons123
NoneType object not subscriptable error in quantize.py Investigating Low Precision Issue about lower bit quantization, including int8, int4, fp8 triaged Issue has been triaged by maintainers
#2818 opened Feb 25, 2025 by HyungjoonYang
@nv-guomingz
2
TRT-LLM 16 -> 17 regression: reduce_fusion with user_buffer plugin on fp8 + llama + L4 bug Something isn't working
#2817 opened Feb 25, 2025 by michaelfeil
2 of 4 tasks
Speculative decoding using Executor API
#2816 opened Feb 24, 2025 by MahmoudAshraf97
1
INT8 KV cache for VLMs
#2815 opened Feb 24, 2025 by ZHITENGLI
[TensorRT-LLM][ERROR] Assertion failed: Do not set crossKvCacheFraction for decoder-only model bug Something isn't working triaged Issue has been triaged by maintainers
#2814 opened Feb 24, 2025 by HPUedCSLearner
2 of 4 tasks
1
(Multi-GPU Triton deployment) MPI_ABORT was invoked on rank 2 in communicator MPI_COMM_WORLD with errorcode 1. bug Something isn't working triaged Issue has been triaged by maintainers
#2813 opened Feb 23, 2025 by jasonngap1
1 of 4 tasks
7
Feature Request: Data Parallelism for Executor API triaged Issue has been triaged by maintainers
#2812 opened Feb 23, 2025 by MahmoudAshraf97
2
MPI Error when build from the souce code bug Something isn't working triaged Issue has been triaged by maintainers
#2811 opened Feb 22, 2025 by yuqie
1
BUG in W4A8_awq-kv-FP8, W-fp8-A-fp8-kv-fp8, in the 0.17.0.post1 bug Something isn't working triaged Issue has been triaged by maintainers
#2810 opened Feb 21, 2025 by white-wolf-tech
4 tasks
@Barry-Delaney
5
Feature Request: Support for Per-Request Logits Post-Processor Registration
#2809 opened Feb 21, 2025 by EmileDqy
Qwen2VL, 报错 TypeError: sequence item 0: expected str instance, NoneType found
#2805 opened Feb 20, 2025 by dong-168
speculative decoding not work
#2804 opened Feb 20, 2025 by biaochen
1
Possible bug in Qwen convert_checkpoint.py Investigating Low Precision Issue about lower bit quantization, including int8, int4, fp8 triaged Issue has been triaged by maintainers
#2803 opened Feb 19, 2025 by mathijshenquet
@Barry-Delaney
2
Running Llama2-70B TP2 on L40s (with fp8 quantization)
#2802 opened Feb 19, 2025 by cquil11
6
Open MPI error while converting model checkpoints
#2801 opened Feb 19, 2025 by adityarajsahu
ProTip! Follow long discussions with comments:>50.