vllm

vLLM Model Optimization Skills

Current vLLM model skills:

• vllm-deepseek-v3-r1-optimization
• vllm-deepseek-v31-optimization
• vllm-deepseek-v32-optimization
• vllm-deepseek-v4-optimization
• vllm-ernie45-optimization
• vllm-gemma4-optimization
• vllm-glm-vlm-ocr-optimization
• vllm-glm45-optimization
• vllm-glm46-glm47-optimization
• vllm-glm5-glm51-optimization
• vllm-gpt-oss-optimization
• vllm-hunyuan3-preview-optimization
• vllm-intern-s1-optimization
• vllm-internvl35-optimization
• vllm-kimi-optimization
• vllm-llama4-optimization
• vllm-mimo-v2-flash-optimization
• vllm-minimax-optimization
• vllm-mistral-small-4-optimization
• vllm-mixtral-quark-int4fp8-moe-optimization
• vllm-moss-vl-optimization
• vllm-nemotron-super-optimization
• vllm-qwen-vlm-omni-asr-optimization
• vllm-qwen3-coder-optimization
• vllm-qwen3-core-optimization
• vllm-qwen3-next-optimization
• vllm-qwen35-optimization
• vllm-qwen36-optimization
• vllm-step35-optimization