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

1mo ago

Recent commits

Latest commits.

feat(cute_dsl/moe): deterministic balanced autotune profile inputs (#3286)
ce43023Lee Nau1mo ago
feat(trace): embed runnable init() in every TraceTemplate (#3221)
b0ec700eigen1mo ago
fix(CI unit tests, cute_dsl, spark): set USER env var before torch._dynamo import for unmapped UIDs (#3314)
de541f1Ka-Hyun Nam1mo ago
feat: Reland support lse in trtllm paged attn kernels (#3116)
a73c281Matt Murphy1mo ago
feat: Expose unpacked topk weights for routed moe (fp4) (#2425)
719ee23Alex Yang1mo ago

Use cudnn 9.23 new API to query workspace with override shape (#3291)

a1b8a60yanqinz21mo ago

feat(logging,trace): cuda-graph-compatible level-5/10 logging + fi_trace template additions/fixes (#3172)

7d1d46eeigen1mo ago

fix typo llama routing issue in trtllm-gen moe (#3303)

ef98312Lain1mo ago

Top contributors

Builders behind this project.