replicate
/

sgl-flash-attn3

Model card Files Files and versions

adarshxs HF Staff commited on Mar 6

Commit

7fe2a6f

·

verified ·

1 Parent(s): 4392d23

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ pip install kernels
 ```python
 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)
@@ -39,7 +39,7 @@ from sgl_kernel.flash_attn import flash_attn_with_kvcache as flash_attn_with_kvc
 Replace with:
 ```python
 from kernels import get_kernel
-_fa3_mod = get_kernel("kernels-community/sgl-flash-attn3", revision="v1")
 flash_attn_varlen_func_fa3 = _fa3_mod.flash_attn_varlen_func
 flash_attn_with_kvcache_fa3 = _fa3_mod.flash_attn_with_kvcache
 ```

 ```python
 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)
 Replace with:
 ```python
 from kernels import get_kernel
+_fa3_mod = get_kernel("kernels-community/sgl-flash-attn3", revision="V1")
 flash_attn_varlen_func_fa3 = _fa3_mod.flash_attn_varlen_func
 flash_attn_with_kvcache_fa3 = _fa3_mod.flash_attn_with_kvcache
 ```