{"slug":"flashinfer","name":"flashinfer","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://flashinfer.ai","repo":"https://github.com/flashinfer-ai/flashinfer","latestVersion":"v0.7.2","latestRelease":"2026-10-16","stars":6736,"starsAsOf":"2026-10-22","description":"FlashInfer: Kernel Library for LLM Serving","descriptionZh":"LLM 服务注意力内核库","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["attention","cuda","distributed-inference","gpu","jit","large-large-models","llm-inference","moe","nvidia","pytorch"],"language":"Cuda","lastPush":"2026-10-22","formerly":null,"packages":[{"registry":"pypi","name":"flashinfer-python","url":"https://pypi.org/project/flashinfer-python/","versionsUrl":"https://pypi.org/project/flashinfer-python/#history","latestVersion":"0.7.0","latestDate":"2026-09-22"}],"recentVersions":[{"version":"v0.7.1","date":"2026-10-09","prerelease":false,"url":"https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.7.1","source":"GitHub Release"},{"version":"v0.7.0.post1","date":"2026-09-29","prerelease":false,"url":"https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.7.0.post1","source":"GitHub Release"},{"version":"v0.7.0","date":"2026-09-22","prerelease":false,"url":"https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.7.0","source":"GitHub Release"},{"version":"v0.6.18.post1","date":"2026-09-05","prerelease":false,"url":"https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.6.18.post1","source":"GitHub Release"},{"version":"v0.6.18","date":"2026-08-29","prerelease":false,"url":"https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.6.18","source":"GitHub Release"}],"alternatives":["tensorrt-llm","gpustack","sglang","llm-d","lmcache","vllm","kserve","stable-diffusion-webui"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：LLM 服务注意力内核库","sources":["oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/flashinfer.json","pages":{"en":"https://aimap.page/en/software/flashinfer/","zh-hans":"https://aimap.page/zh-hans/software/flashinfer/"}}