--- title: "#vllm articles | Hashnode" description: "Explore 83 articles tagged #vllm on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/vllm" --- Tag # #vllm 83 posts · 1 followers [Akshay Suryawanshi](https://hashnode.com/@akshaysuryawanshi) · [4h ago](https://hashnode.com/posts/resizing-vllm-s-kv-cache-without-restarting-the-server/6af533f9230ef56d408e4992) ### [Resizing vLLM’s KV Cache Without Restarting the Server](https://akshaysuryawanshi.hashnode.dev/resizing-vllm-s-kv-cache-without-restarting-the-server?utm_source=hashnode&utm_medium=feed) How I built a vLLM plugin to resize KV cache without restarting, using drain and preserve strategies, CUDA VMM, and Qwen3-32B tests on an H100. 13 min read · [akshaysuryawanshi.hashnode.dev](https://akshaysuryawanshi.hashnode.dev/resizing-vllm-s-kv-cache-without-restarting-the-server?utm_source=hashnode&utm_medium=feed) [reshmi aravind](https://hashnode.com/@raravind007) · [20h ago](https://hashnode.com/posts/from-gpu-pids-to-model-ids-which-vllm-model-is-using-my-gpu/6af45b9e6c263bd581ab7c77) ### [From GPU PIDs to Model IDs: Which vLLM Model Is Using My GPU?](https://practical-ml-systems.hashnode.dev/from-gpu-pids-to-model-ids-which-vllm-model-is-using-my-gpu?utm_source=hashnode&utm_medium=feed) When running LLM inference workloads, tools like nvidia-smi and nvtop help identify GPU utilization, memory consumption, and the processes using those resources. But they don't directly answer another 11 min read · [practical-ml-systems.hashnode.dev](https://practical-ml-systems.hashnode.dev/from-gpu-pids-to-model-ids-which-vllm-model-is-using-my-gpu?utm_source=hashnode&utm_medium=feed) [Shubham Tatvamasi](https://hashnode.com/@ShubhamTatvamasi) · [2d ago](https://hashnode.com/posts/vllm-deep-dive-how-pagedattention-continuous-batching-and-the-v1-engine-serve-llms-in-production/6af1a0c4a32bf9f449f76bd3) ### [vLLM Deep Dive: How PagedAttention, Continuous Batching and the V1 Engine Serve LLMs in Production](https://blog.shubhamtatvamasi.com/vllm-deep-dive-how-pagedattention-continuous-batching-and-the-v1-engine-serve-llms-in-production?utm_source=hashnode&utm_medium=feed) Every layer above it routes, scales and governs requests. vLLM is the layer that turns GPU memory into tokens. 52 min read · [blog.shubhamtatvamasi.com](https://blog.shubhamtatvamasi.com/vllm-deep-dive-how-pagedattention-continuous-batching-and-the-v1-engine-serve-llms-in-production?utm_source=hashnode&utm_medium=feed) [3](https://hashnode.com/posts/vllm-deep-dive-how-pagedattention-continuous-batching-and-the-v1-engine-serve-llms-in-production/6af1a0c4a32bf9f449f76bd3) [404 Founders](https://hashnode.com/@404-founders) · [Nov 5](https://hashnode.com/posts/vllm-cors-vulnerability-cve-2026-115917/6aec14525705da2d5d900a6c) ### [vLLM CORS Vulnerability: The API Key Never Covered /invocations](https://404-founders.com/blog/vllm-cors-vulnerability-cve-2026-115917?utm_source=hashnode&utm_medium=feed) vLLM before 0.32.0 let any web page read model output via the browser, even with --api-key set. Checks and fixes for CVE-2026-115917. 15 min read · [404-founders.com](https://404-founders.com/blog/vllm-cors-vulnerability-cve-2026-115917?utm_source=hashnode&utm_medium=feed) [Andolasoft Inc](https://hashnode.com/@andolasoft) · [Nov 2](https://hashnode.com/posts/air-gapped-ai-analytics-apache-superset-with-local-llms-ollama-and-vllm/6ae881d445913a8a7350d03f) ### [Air-Gapped AI Analytics: Apache Superset with Local LLMs (Ollama and vLLM)](https://andolasoft.hashnode.dev/air-gapped-ai-analytics-apache-superset-with-local-llms-ollama-and-vllm?utm_source=hashnode&utm_medium=feed) Somebody senior has seen a demo. A business user types “which branches had the worst collection efficiency last quarter” and a chart appears. Now they want it in your bank, your ministry or your hospi 2 min read · [andolasoft.hashnode.dev](https://andolasoft.hashnode.dev/air-gapped-ai-analytics-apache-superset-with-local-llms-ollama-and-vllm?utm_source=hashnode&utm_medium=feed) [Aman Karki](https://hashnode.com/@amankarki) · [Oct 26](https://hashnode.com/posts/gpu-fix-faster-on-one-card-slower-on-another-waves/6adf75af7a752cdd73090b42) ### [My GPU fix was 13% faster on one card and 81% slower on another](https://amankarki.hashnode.dev/gpu-fix-faster-on-one-card-slower-on-another-waves?utm_source=hashnode&utm_medium=feed) A vLLM int8 GEMM change, a reviewer with a smaller Ada GPU, and the one idea that explained it: waves 7 min read · [amankarki.hashnode.dev](https://amankarki.hashnode.dev/gpu-fix-faster-on-one-card-slower-on-another-waves?utm_source=hashnode&utm_medium=feed) [Runcrate](https://hashnode.com/@runcrate) · [Oct 26](https://hashnode.com/posts/vllm-on-three-gpus-qwen2-5-7b-tokens-per-second-and-cost-per-1m-tokens-on-rtx-a6000-l40s-and-h100/6adf1b075569314374d2e0a0) ### [vLLM on three GPUs: Qwen2.5-7B tokens per second and cost per 1M tokens on RTX A6000, L40S and H100](https://runcrate.hashnode.dev/vllm-on-three-gpus-qwen2-5-7b-tokens-per-second-and-cost-per-1m-tokens-on-rtx-a6000-l40s-and-h100?utm_source=hashnode&utm_medium=feed) Same model, same benchmark, three rented GPUs: $0.12 to $0.22 per 1M output tokens when the batch is full, $4.86 to $9.47 when it is not. 6 min read · [runcrate.hashnode.dev](https://runcrate.hashnode.dev/vllm-on-three-gpus-qwen2-5-7b-tokens-per-second-and-cost-per-1m-tokens-on-rtx-a6000-l40s-and-h100?utm_source=hashnode&utm_medium=feed) [Theaicommit](https://hashnode.com/@theaicommit) · [Oct 23](https://hashnode.com/posts/why-split-prefill-and-decode-gpus-lose-time-in-the-hand-off-not-the-network/6adbaae4c53825a8ef7c7fa3) ### [Why Split Prefill and Decode GPUs Lose Time in the Hand-Off, Not the Network](https://theaicommit.hashnode.dev/why-split-prefill-and-decode-gpus-lose-time-in-the-hand-off-not-the-network?utm_source=hashnode&utm_medium=feed) Moving the KV cache takes 10 ms, but first-token time hit 1.7 s. How vLLM's pull hand-off stalls the decode loop, and how to size decode slots and fix it. 10 min read · [theaicommit.hashnode.dev](https://theaicommit.hashnode.dev/why-split-prefill-and-decode-gpus-lose-time-in-the-hand-off-not-the-network?utm_source=hashnode&utm_medium=feed) [Aman Karki](https://hashnode.com/@amankarki) · [Oct 17](https://hashnode.com/posts/blockwise-fp8-ada-kernel-4x-too-slow/6ad2ef38195837f31546215e) ### [Blockwise FP8 on Ada GPUs, part 2: my kernel was correct and 4x too slow](https://amankarki.hashnode.dev/blockwise-fp8-ada-kernel-4x-too-slow?utm_source=hashnode&utm_medium=feed) How I found register spills in the main loop, fixed them, and got a 1.42x end-to-end speedup on an L4 8 min read · [amankarki.hashnode.dev](https://amankarki.hashnode.dev/blockwise-fp8-ada-kernel-4x-too-slow?utm_source=hashnode&utm_medium=feed) [Akshay Suryawanshi](https://hashnode.com/@akshaysuryawanshi) · [Oct 16](https://hashnode.com/posts/from-replicas-to-fp8-my-first-vllm-performance-investigation/6ad2ae0da305ffe6691825e0) ### [From Replicas to FP8: My First vLLM Performance Investigation](https://akshaysuryawanshi.hashnode.dev/from-replicas-to-fp8-my-first-vllm-performance-investigation?utm_source=hashnode&utm_medium=feed) Testing vLLM replicas, NVIDIA MPS, and FP8 KV cache and attention on one laptop GPU, measuring throughput, latency, goodput, and answer quality. 10 min read · [akshaysuryawanshi.hashnode.dev](https://akshaysuryawanshi.hashnode.dev/from-replicas-to-fp8-my-first-vllm-performance-investigation?utm_source=hashnode&utm_medium=feed)