LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Other

flashinfer

FlashInfer: Kernel Library for LLM Serving

OtherEmerging

Stars

—

Forks

—

Contributors

8

Last push

1d ago

Recent commits

Latest commits.

fix: One sided MOE A2A warp token policy hangs in some cases, disable… (#3371)
a287034Daniel Stokes13d ago
fix: use explicit .ptr on scalar struct fields in monolithic MLA decode to get cleaner logs (#3458)
02571b5Julien Debache13d ago
bump version to 0.6.13 (#3513)
e8d3131Alex Yang14d ago
docs(comm): NumPy-style docstrings + Deprecated leads for 21 STALE comm APIs (no decorator changes) (#3444)
b69cdf2kangbintNV14d ago
docs(moe): close fused_moe / trtllm_*_moe / CuteDSL MoE doc gaps (#3443)
8e4e15akangbintNV

14d ago

docs(attention): backfill missing/stale Attention/POD/cuDNN/CuteDSL APIs; restore single_prefill_with_kv_cache_return_lse (#3441)

ceb2381kangbintNV14d ago

[docs] Backfill missing docstrings and decorators across kernels (#3456)

e61dfcdkangbintNV14d ago

docs(comm): structural RST refactor for MoeAlltoAll/DCP/Mixed comm (#3445)

4a2c8a5kangbintNV14d ago

Top contributors

Builders behind this project.