0xSero/
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
by 0xSero Python GPL-3.0 licence 200 forks Created Mar 2026 View on GitHub
- Stars
- 1,817
- 22% of 0xSero's stars
- Rank
- #37,672
- of 852,119 repos, top 5%
- In Python
- #6,760
- of 173,305 repos, top 4%
Among 852,119 repos
1.6k–2.5k stars: 15,654 repos, including turboquant
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #37,641
- Next milestone
- +5,395 stars to reach the top 1%
- Popular
- One of 66,549 repos with 1k+ stars