Repository profile

awesome-pro / hiqcache

INT8-quantized hierarchical KV cache for SGLang HiCache. Compresses KV evicted from GPU L1 into the CPU L2 tier, holding 1.78x more tokens in the same host memory. Measured on Qwen3-8B against a BF16 baseline.

cuda
hicache
int8
kv-cache
llm-serving
memory-efficiency
pytorch
quantization
sglang

PythonView on GitHub

Repository overview

Public GitHub metrics and OpenPulse observations

GitHub stars11

Public forks0

Growth · 24h+0 stars

Growth · 7d+0 stars

Growth · 30d+11 stars

Star activity

Last 7 days

16 Oct4 observed days · gaps preserved19 Oct

Observed star growth

Samples or dated GitHub history

24h +0 stars Measured from observations 18 Oct 2026 → 19 Oct 2026

7d +0 stars GitHub history · as of 2026-10-17 11 Oct 2026 → 18 Oct 2026

30d +11 stars GitHub history · as of 2026-10-17 25 Sep 2026 → 18 Oct 2026