FlashInfer Files

FlashInfer: Kernel Library for LLM Serving

This is an exact mirror of the FlashInfer project, hosted at https://github.com/flashinfer-ai/flashinfer. SourceForge is not affiliated with FlashInfer.

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
flashinfer_jit_cache-0.6.16.post3+cu130-cp39-abi3-manylinux_2_28_aarch64.whl	2026-08-08	1.7 GB	0
flashinfer_jit_cache-0.6.16.post3+cu130-cp39-abi3-manylinux_2_28_x86_64.whl	2026-08-08	1.5 GB	0
flashinfer_jit_cache-0.6.16.post3+cu129-cp39-abi3-manylinux_2_28_aarch64.whl	2026-08-08	1.9 GB	0
flashinfer_jit_cache-0.6.16.post3+cu129-cp39-abi3-manylinux_2_28_x86_64.whl	2026-08-08	1.9 GB	0
flashinfer_jit_cache-0.6.16.post3+cu128-cp39-abi3-manylinux_2_28_aarch64.whl	2026-08-08	1.3 GB	0
flashinfer_jit_cache-0.6.16.post3+cu128-cp39-abi3-manylinux_2_28_x86_64.whl	2026-08-08	1.3 GB	0
flashinfer_cubin-0.6.16.post3-py3-none-any.whl	2026-08-08	1.1 GB	0
flashinfer_python-0.6.16.post3-py3-none-any.whl	2026-08-08	15.8 MB	0
flashinfer_python-0.6.16.post3.tar.gz	2026-08-08	11.1 MB	0
README.md	2026-08-07	294 Bytes	0
Release v0.6.16.post3 source code.tar.gz	2026-08-07	6.6 MB	0
Release v0.6.16.post3 source code.zip	2026-08-07	8.5 MB	0
Totals: 12 Items		10.7 GB	0

What's Changed

revert(moe): revert [#3738] SM90 CUTLASS MoE backend (+ dependents [#4025], [#4080]) on release-v0.6.16 by @bkryu in https://github.com/flashinfer-ai/flashinfer/pull/4412

Full Changelog: https://github.com/flashinfer-ai/flashinfer/compare/v0.6.16.post2...v0.6.16.post3

Source: README.md, updated 2026-08-07

Other Useful Business Software

Ship Agents Faster Icon

Ship Agents Faster

Transform your applications and workflows into powerful agentic systems at global scale.

Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.

Get Started Free

99.99% Uptime for MySQL and PostgreSQL Databases Icon

99.99% Uptime for MySQL and PostgreSQL Databases

Sub-second maintenance. 2x read/write performance. Built-in vector search for AI apps.

Cloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.

Try Free

Ship Agents Faster

Transform your applications and workflows into powerful agentic systems at global scale.

Gemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.

Get Started Free

Recommended Projects

LMDeploy
LMDeploy is a toolkit for compressing, deploying, and serving LLMs
tiny-llm
A course of learning LLM inference serving on Apple Silicon
optillm
Optimizing inference proxy for LLMs
vLLM
A high-throughput and memory-efficient inference and serving engine
BentoML
Unified Model Serving Framework