auto-round
by intelIn its repository's words: “PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度”
Facts from GitHub
- Licence
- Apache-2.0 (Apache License 2.0), permissive, our reading
- Activity
- Last push 19 Nov 2026: pushed to in the last 90 days
- Latest release
- not fetched yet
- Stars
- 1.7k
- Main language
- Python
- On GitHub since
- 4 Jan 2024
- Topics
- diffusers, gguf, int4, llms, mxfp4, nvfp4, omni, quantization, rounding, sglang, transformers, vllm, vlms
Other tools in Quantise and convert
- bitsandbytes bitsandbytes-foundation, 8.5k stars
- mergekit arcee-ai, 7.5k stars
- Model-Optimizer NVIDIA, 5.6k stars
- AutoGPTQ AutoGPTQ, 5.1k stars
- llm-compressor vllm-project, 4.0k stars
- llm-awq mit-han-lab, 3.7k stars
Tool data from the GitHub API, fetched 19 Nov 2026, 15:35 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.