CVT, a Computer Vision Toolkit.
-
Updated
Aug 24, 2022 - C
#
int8-quantization
Here are 36 public repositories matching this topic...
Winner solution of mobile AI (CVPRW 2021).
-
Updated
May 14, 2022 - Python
A header-only neural network library for microcontrollers, with partial bare-metal & native-os support.
arduino avr attiny microcontrollers neural-network simple tensorflow lstm gru mnist neural-networks rnn mnist-dataset mlp maths quantization mnist-model mnist-handwriting-recognition int8-quantization quantization-efficient-network
-
Updated
May 11, 2026 - C++
FrostNet: Towards Quantization-Aware Network Architecture Search
computer-vision deep-learning pytorch style-transfer classification object-detection quantization network-architecture semantic-segmentation optimizers quantization-aware-training int8-quantization post-quantization quantization-efficient-network
-
Updated
May 3, 2024 - Python
Quantization Aware Training
-
Updated
Jan 13, 2024 - Python
ATtiny85 arduino example, running an RNN MNIST model via the (internal) 512-Byte EEPROM with ~95% accuracy
microcontrollers cpp11 mnist rnn mnist-classification mnist-dataset attiny85 eeprom mnist-model int8-quantization
-
Updated
Mar 6, 2026 - C++
将端上模型部署过程中，常见的问题以及解决办法记录并汇总，希望能给其他人带来一点帮助。
-
Updated
Aug 17, 2022 - Python
-
Updated
Jun 8, 2023
VB.NET api wrapper for llm-inference chatllm.cpp
bindings api-wrapper llama vb-net vbnet gemma mistral int8 int8-inference int8-quantization cpu-inference chatllm ggml llm-inference qwen
-
Updated
Nov 26, 2024 - Visual Basic .NET
C# api wrapper for llm-inference chatllm.cpp
csharp inference bindings api-wrapper llama gemma mistral int8 int8-inference int8-quantization cpu-inference llm llms chatllm ggml llm-inference qwen
-
Updated
Nov 20, 2024 - C#
Garuda: CVXIF coprocessor optimizing batch-1 attention microkernels with 7.5-9× lower p99 latency. RISC-V INT8 MAC accelerator for transformer inference.
machine-learning neural-network inference simd low-latency systemverilog attention-mechanism risc-v int8 systemverilog-hdl systolic-arrays edge-ai hardware-accelerator int8-quantization cva6 custom-instructions ai-hardware cvxif
-
Updated
Jan 23, 2026 - SystemVerilog
Generating tensorrt model using onnx
pytorch quantization tensorrt onnx int8-inference onnxruntime post-training-quantization int8-quantization tensorrt-inference ptq
-
Updated
Jun 22, 2023 - C++
Corrects your grammar in 5 languages directly in your browser. Powered by an open-source AI model.
javascript chrome-extension nlp machine-learning browser-extension collaborate student-project grammar-checker onnx int8-quantization t5-model github-copilot
-
Updated
Jul 12, 2025 - JavaScript
A fork of convert_to_quant that adds QuIP quantization for INT‑8 models.
-
Updated
May 3, 2026 - Python
TinyML project. This system monitors your room or surrounding with an onboard microphone of Arduino nano BLE sense. Still Under Developement
arduino machine-learning deep-learning quantization tf-data audio-processing spectrograms tflite-conversion tflite-models arduino-nano-33-ble-sense int8-quantization tflite-micro
-
Updated
Oct 18, 2021 - Jupyter Notebook
Python ML for training a custom on-device cry model (knowledge-distilled from YAMNet, INT8, deployed on ESP32-S3)
tensorflow esp32 audio-classification knowledge-distillation audioset tflite cry-detection on-device-ml yamnet tinyml int8-quantization esp32-s3 embedded-ml
-
Updated
May 3, 2026 - Python
CPU face-embedding engine: 13 ms/face ArcFace INT8, 99.65% LFW 10-fold (beats FP32), 96 KB binary, 2.4x faster than ONNX Runtime. C99 + AVX-VNNI.
open-source computer-vision deep-learning neural-network c99 simd biometrics face-recognition low-latency production-ready face-verification onnx arcface insightface embedded-ai edge-ai vnni int8-quantization cpu-inference avx-vnni
-
Updated
Apr 21, 2026 - C
gemma-2-2b-it int8 cpu inference in one file of pure C#
csharp inference quantization gemma int8 inference-engine model-serving int8-inference int8-quantization cpu-inference llm llms llm-serving llm-inference gemma2 gemma2-2b-it
-
Updated
Jun 14, 2025 - C#
g023's TurboXInf 🚀: 2x+ faster inference for Qwen3-1.77B or Qwen3.5-2B on RTX 3060! Custom Triton INT8 GEMV kernels halve memory traffic by fusing dequantization, paired with torch.compile. Hits 113 tok/s (vs 56.4 baseline) with no quality loss with INT8 even better results for INT4. MIT License.
ai kernel gpu gpu-acceleration int8-inference int8-quantization ai-tools ai-inference ai-inference-server int4-quantization
-
Updated
Apr 16, 2026 - Python
Edge-deployable keyword spotter: INT8-quantized DS-CNN on Google Speech Commands, exported to ONNX, with fp32 vs INT8 benchmarks, a live mic demo, and a C++ inference harness.
deep-learning cpp pytorch speech-recognition quantization keyword-spotting wake-word-detection onnx speech-commands edge-ai on-device-ml onnxruntime streamlit tinyml post-training-quantization edge-ml int8-quantization audio-ml ds-cnn
-
Updated
May 6, 2026 - Python
Improve this page
Add a description, image, and links to the int8-quantization topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the int8-quantization topic, visit your repo's landing page and select "manage topics."