intel/neural-speed
An innovative library for efficient LLM inference via low-bit quantization
C++Apache-2.0
Stargazers
- riverscnChina
- xiaoguoerNanjing Jiangsu
- ZJkyle
- intellinjun
- WissamAntounParis-France
- Salma-JamalCairo, Egypt
- aahouziParis, France
- DrRyanHuang
- pragmascriptMunich, Germany
- cocosheFujian, China
- sroeckerStuttgart, Germany
- hdvrai
- LulzxAsia, Earth
- josephrocca
- the-crypt-keeper
- devfacetMA, USA
- AwokeKnowingSan Diego, California
- green-sUnited Kingdom
- swizardlvBeijing
- chittiman
- alanzhai219shanghai
- dnthKuala Lumpur, Malaysia
- jhl9900NanJing
- Minami-su
- gotomypc
- zx33
- onff
- kawamouTsukuba
- atuxhe
- zhenwei-intel
- peteriz
- zafercavdarIstanbul, Turkey
- dytan
- liujingcsMelbourne, Australia
- lioxon
- camenduru