0xSero
★ 1,770turboquant
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
HYSEN LABS 專案目錄
0xSero
來自 0xSero 組織的可信儲存庫、分類與深度解析。
2 個精選開源專案
0xSero
★ 545parchi
Your AI friend right in your browser