Vllm skills

OpenRLHF Training

davila7

Accelerate RLHF training for large models with Ray and vLLM.

High-Performance LLM Serving

davila7

Optimize LLM API deployment with high throughput and low latency.

Jetson LLM Serve

nvidia

Serve LLMs and VLMs on Jetson devices with ease.

Jetson LLM Benchmark

nvidia

Benchmark LLM performance on Jetson devices with JSON output.

Jetson Speculative Decoding

nvidia

Enhance token generation speed on Jetson vLLM servers.