Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mit-han-lab/llm-awq
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
https://github.com/mit-han-lab/llm-awq
Last synced: about 2 months ago
JSON representation
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- Host: GitHub
- URL: https://github.com/mit-han-lab/llm-awq
- Owner: mit-han-lab
- License: mit
- Created: 2023-06-01T00:42:45.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-07-16T00:50:32.000Z (2 months ago)
- Last Synced: 2024-07-17T04:14:39.511Z (2 months ago)
- Language: Python
- Homepage:
- Size: 71.6 MB
- Stars: 2,138
- Watchers: 24
- Forks: 155
- Open Issues: 119
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- Awesome-LLM-Productization - llm-awq - Efficient and accurate low-bit weight quantization (INT3/4) for LLMs, supporting instruction-tuned models and multi-modal LMs. (Models and Tools / LLM Deployment)
- StarryDivineSky - mit-han-lab/llm-awq
- awesome-production-machine-learning - AWQ - han-lab/llm-awq.svg?style=social) - Activation-aware Weight Quantization for LLM Compression and Acceleration. (Model Storage Optimisation)