Inference
- IA
SGLang Omni: Inferencia Multimodal de LLMs con SGLang
Multimodal AI — models that understand images, audio, and video alongside text — has moved from research novelty to production necessity. Document...
- IA
ik_llama.cpp: Fork of llama.cpp with IQ4_NL and Advanced Quantization
The ecosystem around llama.cpp has produced numerous forks, each exploring different optimization strategies for running LLMs efficiently on consumer...