Pinned Loading

1. turboquant-plus turboquant-plus Public

   TurboQuant+: 3-bit KV cache value quantization and group size optimization for long-context LLM inference

   Python 1

2. ChannelQuant ChannelQuant Public

   Near-lossless 4× KV-cache compression for GQA models at ~4.1 bits/value — per-channel-key INT4 + static outlier ROM, with a reproducible reference model and paper.

   Python

3. LonghornSilicon/lambda-kve LonghornSilicon/lambda-kve Public

   Read-only mirror of the KVE (KV Cache Engine) block of the Lambda monorepo (LonghornSilicon/lambda). ChannelQuant KV-cache codec. Develop in the monorepo; this repo is auto-mirrored.

   Python

4. LonghornSilicon/lambda-acu LonghornSilicon/lambda-acu Public

   Read-only mirror of the ACU (Attention Compute Unit) umbrella block of the Lambda monorepo (LonghornSilicon/lambda). MatE + VecU + precision controller — the Q·Kᵀ→softmax→P·V datapath. Develop in t…

   Python

5. evoplace evoplace Public

   LLM-guided evolutionary VLSI placement: beating DreamPlace with evolved objective functions

   Python 1 1

6. covenant covenant Public

   Contract-driven GPU analytical placer (DREAMPlace fork overlay) with a noise-calibrated evaluation protocol, paired multi-seed CIs, liveness gates, calibration arms.

   Python