Dev
GitHub repos gaining traction - what high-signal users are starring and what's climbing the board, captured daily and enriched from GitHub. Raw material for spotting new tech and patterns worth building on.
2,991
repos tracked
117
surfaced this week
232
created < 30d
Python
top language
8 repos
-
CPU exercise: implement KV caching inside attention.
-
Distributed transactional key-value database, originally created to complement TiDB
-
Apache Kvrocks is a distributed key value NoSQL database that uses RocksDB as storage engine and is compatible with Redis protocol.
-
High Performance Hierarchical KV Cache Planner
-
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
-
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
-
Working recipe to serve DeepSeek-V4-Flash across two NVIDIA DGX Spark (GB10) nodes with vLLM (TP=2, FP8 KV, MTP) over a RoCE/RDMA link — Docker image, launch scripts, RDMA/NCCL setup, and the gotchas.
-
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.