LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Python

flashinfer

FlashInfer: Kernel Library for LLM Serving

PythonEmerging

Stars

—

Forks

—

Contributors

8

Last push

2mo ago

Recent commits

Latest commits.

fix(cute_dsl/moe): make autotuner bucket configuration adapt to runtime input (#3216)
e6ac7ccLee Nau2mo ago
bump version to 0.6.11 (#3245)
cb44e7dAlex Yang2mo ago
fix(mla): widen page index to int64_t to avoid 32-bit overflow (#3136)
d885b71Qi Zhang (qizh)2mo ago
cute-dsl fmha prefill (cubin integration): remove front-padding, add attention_sink, and pdl support (#3181)
89af11cLi Min2mo ago
Support Sigmoid (sigmoid+topk) routing function (#2869)
417e59fEdalatiAli2mo ago

cute_dsl/moe: drop redundant Python-side moe_sort buffer init (#3226)

979644fLee Nau2mo ago

fix: add jitter to cubin download backoff (#3169)

55a9eeaPaul Luh2mo ago

fix: fused MoE autotuning correctness issues by filtering clusterDimZ (#3227)

2bb1f85Wei Zhao2mo ago

Top contributors

Builders behind this project.