PrototypeCommon
novitalabs/pegaflow
High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.
- Owner
- novitalabs (organization)
- Stars
- Stars: 221
- Forks
- Forks: 31
- Language
- Rust
- License
- Apache-2.0
- Created
- 2026
- Topics
- inferencekv-cachellmvllm
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by novitalabs
All 3 repos by novitalabs- novitalabs/AnimateAnyoneStars: 787PythonBeta
- novitalabs/sd-webui-cleanerStars: 339JavaScriptAlpha
Nearby in Rust
All Rust repos- DawnMagnet/hearthstone-linux-guiStars: 221RustPrototype
- slaterain/nv-rsStars: 221RustPrototype
- crystalmasta/unbihexStars: 221RustPrototype
- discord/loquiStars: 221RustPrototype
- openrr/kStars: 221RustPrototype
- softprops/dynomiteStars: 221RustPrototype