mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-04-20 14:29:22 +00:00
Fix kt-kernel for new wrapper (#1588)
* update README for kt-kernel * style: format C++ and Python code in kt-kernel - Format C++ files: task_queue, ext_bindings, and MoE operators - Format Python utility modules: amx, llamafile, and loader - Improve code readability and consistency
This commit is contained in:
@@ -6,15 +6,17 @@ import ctypes
|
||||
from ..experts_base import BaseMoEWrapper
|
||||
from .loader import SafeTensorLoader
|
||||
from kt_kernel_ext.moe import MOEConfig
|
||||
|
||||
try:
|
||||
from kt_kernel_ext.moe import AMXInt4_MOE, AMXInt8_MOE
|
||||
|
||||
_HAS_AMX_SUPPORT = True
|
||||
except (ImportError, AttributeError):
|
||||
_HAS_AMX_SUPPORT = False
|
||||
AMXInt4_MOE, AMXInt8_MOE = None, None
|
||||
|
||||
from typing import Optional
|
||||
|
||||
|
||||
|
||||
class AMXMoEWrapper(BaseMoEWrapper):
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user