Skip to content

Issues: NVIDIA/TensorRT-Model-Optimizer

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

88 Open 62 Closed
88 Open 62 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

Which instructions should I follow to quant my model from bf16 to nvfp4?
#164 opened Mar 28, 2025 by ghostplant
What is pre_quant_scale?
#163 opened Mar 26, 2025 by dingjingzhen
3
Unable to quantize pytorch model using huggingface export
#161 opened Mar 23, 2025 by ishan-modi
2
slower when quantize whole bert model than quantize only ffn
#159 opened Mar 20, 2025 by DamonsJ
2
issue about eagle
#158 opened Mar 20, 2025 by white-wolf-tech
Large model offloaded to huggingface accelerate is not able to export the weights using unified export. bug Something isn't working
#157 opened Mar 18, 2025 by michaelfeil
@Edwardf0t1
2
int4 quantization output onnx does not load bug Something isn't working
#156 opened Mar 13, 2025 by thejaswi01
modelopt corrupts output onnx
#154 opened Mar 11, 2025 by thejaswi01
2
Missing Support for Qwen2Moe
#153 opened Mar 11, 2025 by michaelfeil
13
pi0 support?
#151 opened Mar 9, 2025 by johnnynunez
4
What is the Precision of the Linear Layer Operations in the Attention Module of the DeepSeek R1 FP4 Model?
#150 opened Mar 7, 2025 by charmin161
4
PyTorch Quantization Failed to Quantize Scaled Dot Product
#149 opened Mar 7, 2025 by YixuanSeanZhou
@jingyu-ml
8
[RFC] TensorRT Model Optimizer - Product Roadmap roadmap
#146 opened Mar 6, 2025 by omrialmog
@omrialmog
Not support torch.compile() ?
#145 opened Mar 5, 2025 by Vieeo
sm_100 not defined for option gpu-name when running calibration in DeepSeek
#144 opened Mar 4, 2025 by imenselmi
1
Quantized model size is larger than the original model
#143 opened Mar 1, 2025 by Urania880519
@riyadshairi979
5
the consistency between modelopt and trt is quite different?
#140 opened Feb 24, 2025 by 666DZY666
@riyadshairi979
4
trt-modelopt is not compatible with pytorch FSDP？
#139 opened Feb 21, 2025 by Vieeo
3
Restore functionality: lm_head option to disable quantization
#138 opened Feb 20, 2025 by michaelfeil
@cjluo-nv
4
UNet cannot be quantized with assertion error
#136 opened Feb 19, 2025 by 4a16dick
@riyadshairi979
can modelopt export trt calib cache？
#135 opened Feb 19, 2025 by 666DZY666
@riyadshairi979
1
modelopt2trt：model inference time is much slower!
#134 opened Feb 19, 2025 by 666DZY666
2
More modes for model opt quantization than halving the batch size
#133 opened Feb 18, 2025 by michaelfeil
1
Support SequenceClassifcation Models
#132 opened Feb 18, 2025 by michaelfeil
How to sparse the specified model parameters
#130 opened Feb 13, 2025 by Vieeo
ProTip! Updated in the last three days: updated:>2025-03-27.