PrototypeCommon
chelsea0x3b/llama-dfdx
LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!
- Owner
- chelsea0x3b (personal account)
- Stars
- Stars: 112
- Forks
- Forks: 5
- Language
- Rust
- License
- MIT
- Created
- 2023
- Topics
- cudadeep-learninginferencelanguage-modelllamaneural-networkrustrust-lang
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by chelsea0x3b
All 3 repos by chelsea0x3b- chelsea0x3b/dfdxStars: 1,943RustBeta
- chelsea0x3b/cudarcStars: 1,239RustBeta
Nearby in Rust
All Rust repos- rudy-io/moli-osStars: 112RustPrototype
- sawhorse3d/sawhorseStars: 112RustPrototype
- PZW152/one-click-eu-lordStars: 112RustPrototype
- hoodie/toastifyStars: 112RustPrototype
- EmilHernvall/hermesStars: 112RustPrototype
- JanLikar/cargo-cloneStars: 112RustPrototype