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.
3,195
repos tracked
105
surfaced this week
193
created < 30d
Python
top language
9 repos
-
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)
-
A shared, org-authenticated GitHub read relay and cache.
-
CPU exercise: implement KV caching inside attention.
-
High Performance Hierarchical KV Cache Planner
-
Cache your API calls with a single line of code. No mocks, no fixtures. Just faster, cleaner code.
-
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
-
1D dilated causal convolutions with extreme caching for 5µs inference on an FPGA
-
A modern replacement for Redis and Memcached
-
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.