sgl-flash-attn3

61
3
license:bsd-3-clause
by
kernels-community
Other
OTHER
New
61 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Code Examples

Usagebash
pip install kernels
Usagepython
from kernels import get_kernel

fa3 = get_kernel("kernels-community/sgl-flash-attn3", revision="v1")

fa3.flash_attn_varlen_func(q, k, v, cu_seqlens_q, cu_seqlens_k, causal=True)
fa3.flash_attn_with_kvcache(q, k_cache, v_cache, cache_seqlens=cache_seqlens, causal=True)
fa3.is_fa3_supported()  # True on H100/H200

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.