smoothquant

Here are 5 public repositories matching this topic...

intel / neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

sparsity pruning quantization knowledge-distillation auto-tuning int8 low-precision quantization-aware-training post-training-quantization awq int4 large-language-models gptq smoothquant sparsegpt fp4 mxformat

Updated Sep 4, 2026
Python

ModelTC / LightCompress

Star

[EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video generative models.

benchmark deployment tool evaluation pruning quantization wan awq large-language-models llm token-pruning vllm smoothquant token-reduction mixtral internlm2 token-merging deepseek-v3

Updated May 14, 2026
Python

fei121 / Qwen3-8B-Quantization

Star

Qwen3-8B quantization study across vLLM, TensorRT-LLM, AutoRound, INT8, and MXFP4

quantization int8 vllm smoothquant tensorrt-llm autoround qwen3 mxfp4

Updated Aug 8, 2026
Python

luckystar-pear / llm-compress

Star

Compress context data to optimize memory and performance in C++ large language model applications within the llm-cpp toolkit.

nlp cli lightweight sparsity tool evaluation developer-tools pruning wan awq llm fastertransformer smoothquant token-reduction codellama internlm2 token-merging llama3 deepseek-v3

Updated Sep 5, 2026
C++

lyell0710 / LLM_Quantization

Star

GPTQ / AWQ / SmoothQuant 从零实现：同模型、同评测协议、同量化网格下的控制变量对照 —— GPTQ 收回 RTN 损失 61.6%、AWQ 31.9%、叠加仅再 +1.0pp

pytorch quantization awq llm gptq smoothquant

Updated Aug 29, 2026
Python

Add this topic to your repo

To associate your repository with the smoothquant topic, visit your repo's landing page and select "manage topics."

Learn more