qualcomm/aimet

View on GitHub

AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

Stars: 2.7k
Forks: 464
Open beginner issues: 0
Indexed issues: 25

Dominant language: Python
License: No license data
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

25 open issues indexed

Docs snippets for AdaScale/SpinQuant call _prefill_inputs and _set_tensors_to_output_n_bit_symmmetric with non-existent keyword arguments Open

Difficulty 2/5 1-3 hours Newbie friendliness 45/100

qualcomm/aimet#4112 · Opened Aug 30, 2026
have mismatching datatypes. 0x416 != 0x232 Open

bug

qualcomm/aimet#4104 · 1 comment · 1 assignee · Opened Jun 10, 2026
[BUG] LiteMP FP16 mixed precision cannot be deployed via qnn-onnx-converter on QAIRT 2.33.0 Open

community QNN

qualcomm/aimet#4102 · 5 comments · 1 assignee · Opened Jun 4, 2026
How to Disable Concat Quantization Nodes, and how to Share the Same Quantization Parameters Across Multiple Layers Open

question

qualcomm/aimet#4101 · 3 comments · 1 assignee · Opened May 26, 2026
Support GPTQ for LLMs INT4 quantization Open

question

qualcomm/aimet#4100 · 2 comments · 1 assignee · Opened May 19, 2026
Examples.torch.quantize ERROR Open

aimet-torch llm

qualcomm/aimet#4095 · 3 comments · 1 assignee · Opened Apr 29, 2026
AIMET Quantized Model Experiences Severe Accuracy Drop After QAIRT Conversion Open

aimet-onnx

Difficulty 4/5 3-5 days Newbie friendliness 48/100

qualcomm/aimet#4094 · 3 comments · Opened Apr 24, 2026
run lpbq demo Qwen2.5-0.5B-Instruct convert qnn cpp crash Open

aimet-onnx documentation llm

qualcomm/aimet#4091 · 1 assignee · Opened Apr 14, 2026
QAT with Aimet: Gradient & Training Behavior of param_quantizers min/max under two quant_schemes Open

aimet-torch question

Difficulty 4/5 3-5 days Newbie friendliness 35/100

qualcomm/aimet#4087 · 4 comments · Opened Mar 25, 2026
Quantitative analysis (qwen-3.5) Open

community enhancement llm Medium

qualcomm/aimet#4083 · 2 comments · 1 assignee · Opened Mar 12, 2026
Asymmetric Quantization Offset Overflow Issue with Large Activation Ranges Open

question waiting on more information

qualcomm/aimet#4072 · 2 comments · 1 assignee · Opened Jan 30, 2026
quantize qwen3-vl Open

enhancement in-progress llm

qualcomm/aimet#4063 · 3 comments · 1 assignee · Opened Jan 22, 2026
QuantSim accuracy is close to FP32, but inference result is incorrect when running with Genie (QNN 2.30, AIMET 2.0.0) Open

llm question

qualcomm/aimet#4057 · 4 comments · 6 reactions · 1 assignee · Opened Dec 30, 2025
Publish Python 3.12 wheels Open

enhancement in-progress installation

qualcomm/aimet#4027 · 6 comments · 2 reactions · 1 assignee · Opened Aug 29, 2025
QNN_TARGET_ARCH when running qnn-model-lib-generator and qnn-context-binary-generator Open

bug QNN waiting on more information

qualcomm/aimet#4022 · 3 comments · 1 assignee · Opened Aug 25, 2025
Deekseek quant support Open

documentation enhancement llm

qualcomm/aimet#3815 · 1 comment · 1 assignee · Opened Feb 17, 2025
Read this FIRST! Open

community

Difficulty 1/5 Under an hour Newbie friendliness 15/100

qualcomm/aimet#3730 · 1 reaction · Opened Jan 14, 2025
How to estimate export onnx-model time Open

question waiting on more information

qualcomm/aimet#3269 · 1 comment · 1 assignee · Opened Aug 26, 2024
How to get a Qoperator format ONNX model after quantization? Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

qualcomm/aimet#2825 · 4 comments · 2 reactions · Opened Mar 18, 2024
examples for YOLOv5 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

qualcomm/aimet#2809 · 4 comments · Opened Mar 5, 2024
CUDA out of memory Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

qualcomm/aimet#2807 · 6 comments · Opened Mar 5, 2024
The quantization parameters of encodings are inconsistent with the quantization parameters in embeeding.onnx Open

qualcomm/aimet#2680 · 3 comments · 1 assignee · Opened Jan 29, 2024
QAT issue of yolox Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

qualcomm/aimet#2679 · Opened Jan 29, 2024
Support LLM large models Open

question

Difficulty 5/5 Over a week Newbie friendliness 25/100

qualcomm/aimet#2678 · 8 comments · Opened Jan 28, 2024
Does the bn reestimation really work? Open

qualcomm/aimet#1974 · 6 comments · 1 assignee · Opened Mar 1, 2023

qualcomm/aimet

Get new issues in your inbox