{"slug": "stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server", "title": "Stop Crashing and Start Cooking with vLLM on AMD and Lemonade Server", "summary": "A developer achieved 3x better batch throughput with Qwen3.5 by fixing vLLM on AMD's Strix Halo using the Lemonade Server, enabling more efficient AI inference on AMD hardware.", "body_md": "How I Fixed vLLM on Strix Halo and Got 3x Better Batch Throughput with Qwen3.5\nContinue reading on Towards AI »", "url": "https://wpnews.pro/news/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server", "canonical_source": "https://pub.towardsai.net/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server-bef66caf5db0?source=rss----98111c9905da---4", "published_at": "2026-06-24 12:31:01+00:00", "updated_at": "2026-06-24 12:46:20.285341+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "ai-tools"], "entities": ["vLLM", "AMD", "Strix Halo", "Lemonade Server", "Qwen3.5", "Towards AI"], "alternates": {"html": "https://wpnews.pro/news/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server", "markdown": "https://wpnews.pro/news/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server.md", "text": "https://wpnews.pro/news/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server.txt", "jsonld": "https://wpnews.pro/news/stop-crashing-and-start-cooking-with-vllm-on-amd-and-lemonade-server.jsonld"}}