--- title: "#sglang articles | Hashnode" description: "Explore 7 articles tagged #sglang on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/sglang" --- Tag # #sglang 7 posts · 0 followers [Jahn](https://hashnode.com/@conatusai) · [Aug 26](https://hashnode.com/posts/sglang-outputs-endless-repetition-on-nvfp4-models-the-fp8-lm-head-bug/6a8e6c6c69f489e4b799278a) ### [SGLang outputs endless repetition on NVFP4 models: the FP8 lm\_head bug](https://conatusai.hashnode.dev/sglang-outputs-endless-repetition-on-nvfp4-models-the-fp8-lm-head-bug?utm_source=hashnode&utm_medium=feed) Your NVFP4 model serves fine on vLLM but outputs an endlessly repeated phrase on SGLang, from the very first token, even on a trivial prompt. The response content comes back empty, every request ends 3 min read · [conatusai.hashnode.dev](https://conatusai.hashnode.dev/sglang-outputs-endless-repetition-on-nvfp4-models-the-fp8-lm-head-bug?utm_source=hashnode&utm_medium=feed) [Robert Collins](https://hashnode.com/@robbiemu) · [Jul 1](https://hashnode.com/posts/dgx-spark-inference-keeping-good-habits-around-local-inference/6a451dbc63a097b73d3f139c) ### [dgx-spark-inference - Keeping good habits around local inference](https://selfenrichment.hashnode.dev/dgx-spark-inference-keeping-good-habits-around-local-inference?utm_source=hashnode&utm_medium=feed) Local inference has a habit of becoming folklore. You launch a model from a shell history fragment you can never quite find again. A context setting lives in a note somewhere. A faster quantization ge 8 min read · [selfenrichment.hashnode.dev](https://selfenrichment.hashnode.dev/dgx-spark-inference-keeping-good-habits-around-local-inference?utm_source=hashnode&utm_medium=feed) [Shaun Liew](https://hashnode.com/@shaunliew20) · [May 16](https://hashnode.com/posts/running-qwen3-vl-on-dgx-spark-transformers-vs-vllm-vs-sglang/6a0824a15adec4606348738f) ### [Running Qwen3-VL on DGX Spark: Transformers vs vLLM vs SGLang](https://shaunliew.hashnode.dev/running-qwen3-vl-on-dgx-spark-transformers-vs-vllm-vs-sglang?utm_source=hashnode&utm_medium=feed) A hands-on inference benchmark across three frameworks on a desk-sized AI supercomputer. 14 min read · [shaunliew.hashnode.dev](https://shaunliew.hashnode.dev/running-qwen3-vl-on-dgx-spark-transformers-vs-vllm-vs-sglang?utm_source=hashnode&utm_medium=feed) [Jangwook Kim](https://hashnode.com/@effloow) · [Apr 22](https://hashnode.com/posts/llm-inference-engines-compared-vllm-sglang-tgi-2026/69e84d98f6cb79f281dd8305) ### [LLM Inference Engines Compared 2026: vLLM vs SGLang vs TGI vs MAX](https://effloow.hashnode.dev/llm-inference-engines-compared-vllm-sglang-tgi-2026?utm_source=hashnode&utm_medium=feed) Serving a large language model in production is a solved problem — until your traffic doubles, your structured output pipeline slows to a crawl, or your cloud bill arrives. The choice of inference engine determines how many GPUs you actually need, ho... 11 min read · [effloow.hashnode.dev](https://effloow.hashnode.dev/llm-inference-engines-compared-vllm-sglang-tgi-2026?utm_source=hashnode&utm_medium=feed) [Aditya Gupta](https://hashnode.com/@adiyogiarts) · [Mar 28](https://hashnode.com/posts/benchmarking-llm-serving-vllm-tensorrt-llm-sglang-performanc/69c76d6ab0a40952e69be3c5) ### [Benchmarking LLM Serving: vLLM, TensorRT-LLM & SGLang Performance](https://adiyogiarts.hashnode.dev/benchmarking-llm-serving-vllm-tensorrt-llm-sglang-performanc?utm_source=hashnode&utm_medium=feed) Benchmarking LLM Serving: vLLM, TensorRT-LLM & SGLang Performance Benchmarking Large Language Model (LLM) serving... 4 min read · [adiyogiarts.hashnode.dev](https://adiyogiarts.hashnode.dev/benchmarking-llm-serving-vllm-tensorrt-llm-sglang-performanc?utm_source=hashnode&utm_medium=feed) [mao mao](https://hashnode.com/@maomao) · [Dec 10, 2025](https://hashnode.com/posts/the-kv-cache-dilemma-why-llm-inference-needs-to-forget-to-scale/6938dcc22f6a0339f388b236) ### [The KV Cache Dilemma: Why LLM Inference Needs to "Forget" to Scale?](https://maomao.hashnode.dev/the-kv-cache-dilemma-why-llm-inference-needs-to-forget-to-scale?utm_source=hashnode&utm_medium=feed) Have you ever wondered why the 10th turn of a conversation with an LLM feels just as fast as the first? Mathematically, this shouldn’t happen. As the context grows (History + New Question), the computation required to generate the next token should i... 3 min read · [maomao.hashnode.dev](https://maomao.hashnode.dev/the-kv-cache-dilemma-why-llm-inference-needs-to-forget-to-scale?utm_source=hashnode&utm_medium=feed)