Skip to content

Issues: NVIDIA/TensorRT-Model-Optimizer

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

87 Open 101 Closed
87 Open 101 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

5090 error
#218 opened Jun 17, 2025 by lloveapple
support for python 3.13 feature request New feature or request
#217 opened Jun 16, 2025 by yash-s20
@kevalmorabia97
1
can not restore model
#216 opened Jun 16, 2025 by reza-shahriari
INT8 to FP8 scale conversion
#215 opened Jun 15, 2025 by roamiri
@i-riyad
3
flux-dev 5090
#213 opened Jun 13, 2025 by lloveapple
the error for quantize.py
#212 opened Jun 13, 2025 by lloveapple
1
Bugs in the speculative decoding example bug Something isn't working
#211 opened Jun 11, 2025 by Framartin
1
@yeyu-nvidia
1
Explicit quantization in PyTorch before ONNX leads to slower TRT engine than ONNX PTQ bug Something isn't working
#207 opened Jun 8, 2025 by liukang1811
@i-riyad
6
Apart from fp8, are there any plans to directly support vllm inference with awq in the future feature request New feature or request
#204 opened May 28, 2025 by dingjingzhen
get_modelike_from_algo_cfg doesn't accept QuantizeAlgorithmConfig, but it's typing says it should bug Something isn't working
#201 opened May 21, 2025 by ORippler
[BUG] FP8 real_quantization doesnt work with block_sizes bug Something isn't working
#193 opened May 9, 2025 by ishan-modi
@meenchen @realAsma
1
is fp8 quantization with block-wise/per-token/per-channel supported feature request New feature or request
#192 opened May 9, 2025 by YSF-A
1
What is the difference of config in mtq.quantize() and config in TensorQuantizer
#190 opened May 6, 2025 by YSF-A
@realAsma
1
Support for W4A16 and W4A8 Quantization in TensorRT Model Optimizer feature request New feature or request
#189 opened Apr 30, 2025 by david-PHR
4
Cannot serve modelopt quantized nvfp4 model on TensorRT LLM bug Something isn't working
#187 opened Apr 27, 2025 by enisaras
@meenchen
2
[BUG] modelopt restore quantized models using 'AutoModelForCausalLM.from_pretrained' doesn't work for mixtral-8x7b bug Something isn't working
#186 opened Apr 27, 2025 by wanzhenchn
3
Support more Quantization methods for "onnx_ptq"? feature request New feature or request
#184 opened Apr 24, 2025 by s101010tw
@i-riyad
[BUG] Issue processing NF4 double quantization bug Something isn't working
#183 opened Apr 22, 2025 by ishan-modi
1
@meenchen
3
Qwen2_MoE AWQ(w4a16/w4a8) quantization failed with Nan AssertionError
#182 opened Apr 22, 2025 by wanzhenchn
@meenchen
2
Torch Quantization: Allow restoring quantized model and re-running calibration on new data (PTQ) feature request New feature or request
#179 opened Apr 16, 2025 by david-PHR
@realAsma
1
Run w4a8 quant for deepseek r1 on 8xH20 OOM
#177 opened Apr 14, 2025 by Kiokana
1
Explicit INT8 Quantization Fails to Fuse Concat-Conv Block Compared to Implicit Mode needs trt triage Need TensorRT teams help
#174 opened Apr 9, 2025 by patrickgrommelt
@i-riyad
5
Getting Real quantization not supported for this format error when using mtq.compress(model)
#171 opened Apr 5, 2025 by RivenSama
@meenchen
1
SDPA Int8 Quantisation using MTQ
#170 opened Apr 4, 2025 by satya-penamakuri
@jingyu-ml
3
slower when quantize whole bert model than quantize only ffn
#159 opened Mar 20, 2025 by DamonsJ
11
ProTip! Type g i on any issue or pull request to go back to the issue listing page.