Unverified Commit ca63f075 authored by fzyzcjy's avatar fzyzcjy Committed by GitHub
Browse files

Revert "Fix FA4 import cause moe_fused_gate output be illegal memory" (#10432)

parent f9ee6ae1
...@@ -9,6 +9,11 @@ try: ...@@ -9,6 +9,11 @@ try:
except: except:
raise ImportError("Can not import sgl_kernel. Please check your installation.") raise ImportError("Can not import sgl_kernel. Please check your installation.")
try:
from ._fa4_interface import flash_attn_varlen_func as flash_attn_varlen_func_v4
except ImportError:
flash_attn_varlen_func_v4 = None
@lru_cache(maxsize=1) @lru_cache(maxsize=1)
def is_fa3_supported(device=None) -> bool: def is_fa3_supported(device=None) -> bool:
...@@ -244,8 +249,9 @@ def flash_attn_varlen_func( ...@@ -244,8 +249,9 @@ def flash_attn_varlen_func(
ver=3, ver=3,
): ):
if ver == 4: if ver == 4:
from ._fa4_interface import flash_attn_varlen_func as flash_attn_varlen_func_v4 assert (
flash_attn_varlen_func_v4 is not None
), "FA4 is not available, please check your installation."
# Using `(-1, -1)` as no sliding window causes correctness issues for FA4. # Using `(-1, -1)` as no sliding window causes correctness issues for FA4.
if window_size == (-1, -1): if window_size == (-1, -1):
window_size = (None, None) window_size = (None, None)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment