19 lines
249 B
Python
19 lines
249 B
Python
QK4_1 = 32
|
|
|
|
|
|
def dequantize_q4_1_triton():
|
|
pass
|
|
def dequantize_q4_1_pytorch():
|
|
pass
|
|
|
|
def quantize_q4_1_triton():
|
|
pass
|
|
def quantize_q4_1_pytorch():
|
|
pass
|
|
|
|
def q4_1_fused_gemm_triton():
|
|
pass
|
|
def q4_1_fused_gemm_pytorch():
|
|
pass
|
|
|