From-scratch Rust+CUDA LLM inference engine for RTX 5090 (sm_120a) — NVFP4, MoE, MTP speculative decoding, tuned against measured hardware limits
Related
ZhouTimeMachine/JVT: JVT: Just Video Transformer makes pixel-space video diffusion simple
JVT: Just Video Transformer makes pixel-space video diffusion simple
WinnerSpecialist/Gemini-Config-Checker-: Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
Chain region scanner: find proxy configs that get you into Google AI Studio and Gemini (signed-in browser check, anti-DPI, Windows/macOS/Linux/Android)
BehemothDyer/stable-diffusion-atelier: Atelier notes for local diffusion — samplers, LoRAs and VRAM plans.
Atelier notes for local diffusion — samplers, LoRAs and VRAM plans.