GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
quantizationHere are 4,049 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
nlp agent ai transformers moe llama gpt lora quantization gemma fine-tuning peft large-language-models llm rlhf instruction-tuning qlora qwen deepseek llama3
Faster Whisper transcription with CTranslate2
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
nlp llama lora quantization alpaca plm pre-trained-language-models large-language-models llm llama-2 alpaca-2
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
machine-learning deep-learning bitcoin blockchain fintech quantitative-finance trademarks quantization funds strategies backtest quantitative-trading pytrade qlib quant-trade trade-bot quant-trader
A vector index built on TurboQuant, written in Rust with Python bindings
python rust neon embeddings simd nearest-neighbor quant ann quantization avx512 embedding faiss rag vector-search turboquant
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
machine-learning deep-learning c99 simd transformer moe avx2 quantization memory-efficient from-scratch systems-programming inference-engine mixture-of-experts zero-dependencies linear-attention cpu-inference llm llm-inference mxfp4 kimi-k3
Accessible large language models via k-bit quantization for PyTorch.
Lossy PNG compressor — pngquant command based on libimagequant library
c palette quality png png-compression conversion smaller stdin image-optimization quantization pngquant
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
nlp deep-learning transformers inference pytorch transformer quantization large-language-models llms
Fast inference engine for Transformer models
deep-neural-networks deep-learning cpp neon machine-translation openmp parallel-computing cuda inference avx intrinsics avx2 neural-machine-translation opennmt quantization gemm mkl thrust transformer-models onednn
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
cuda triton attention vit quantization video-generation mlsys inference-acceleration efficient-attention llm llm-infra video-generate
State-of-the-art LLM compression, built for production inference with vLLM
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
ai mcp interview interview-questions quantization questions-and-answers agents interview-preparation ai-agents fine-tuning rag ai-engineering llm llm-inference
🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools
training optimization intel transformers inference pytorch quantization onnx tflite onnxruntime graphcore habana
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Sparsity-aware deep learning inference runtime for CPUs
nlp performance computer-vision inference machinelearning pruning object-detection pretrained-models quantization cpus onnx sparsification llm-inference deepsparse
A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Add this topic to your repoTo associate your repository with the quantization topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |