High Throughput skills
Free agent skills tagged high throughput, ready to install into any SKILL.md-compatible agent.
3 skills
High-Performance LLM Serving
davila7
Optimize LLM API deployment with high throughput and low latency.
Developer ToolsintermediatePython · Shell30.2k repo
vLLM Serving
nousresearch
High-performance LLM serving for optimized inference.
Developer ToolsintermediatePython · Shell228.5k repo
TensorRT-LLM
davila7
Optimize LLM inference for NVIDIA GPUs with TensorRT.
Developer ToolsadvancedPython · Shell30.2k repo