← Trending

Tangerine Index lists products launched since ChatGPT and people's reactions to them.

OSCAR

github.com

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

Open source

Visit github.comexternal siteGitHub563 starsexternal site

Reactions (1)

Similar products

by description similarity

  1. kvpress

    LLM KV cache compression made easy

    GitHub1,249 starsgithub.comOpen sourcelatest reaction

  2. KVBoost

    chunk-level KV cache reuse for HuggingFace, 5–48x faster TTFT

    Hacker News20 ptspythongiant.github.iolatest reaction

  3. exllamav3

    An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

    GitHub1,810 starsgithub.comLibraryOpen sourcelatest reaction

  4. Taliesin

    bit-exact KV-cache restore, 21x faster, cross-GPU verified

    Hacker News10 ptsmedium.comlatest reaction

  5. An RDMA/Infiniband Distributed Cache for Fast Inference and Training

    A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

    Hacker News16 ptsGitHub47 starsgithub.comOpen source5 reactionslatest reaction