Fast Inference skills
Free agent skills tagged fast inference, ready to install into any SKILL.md-compatible agent.
3 skills
GPTQ Quantization
davila7
Efficiently deploy large LLMs on consumer GPUs with minimal loss.
Developer ToolsintermediatePython · Shell30.2k repo
SGLang
davila7
Fast structured generation and serving for LLMs.
AI & AgentsintermediatePython · Shell30.2k repo
A
AWQ Quantization
davila7
Optimize large models with 4-bit quantization.
Developer ToolsintermediatePython · Shell30.2k repo