|
Up
|
|
|
|
|
add.cl
|
|
|
|
|
add_id.cl
|
|
|
|
|
argsort.cl
|
|
|
|
|
clamp.cl
|
|
|
|
|
concat.cl
|
|
|
|
|
conv2d.cl
|
|
|
|
|
conv2d_f16_f32.cl
|
|
|
|
|
cpy.cl
|
|
|
|
|
cumsum.cl
|
|
|
|
|
cvt.cl
|
|
|
|
|
diag.cl
|
|
|
|
|
diag_mask_inf.cl
|
|
|
|
|
div.cl
|
|
|
|
|
embed_kernel.py
|
|
|
|
|
exp.cl
|
|
|
|
|
expm1.cl
|
|
|
|
|
fill.cl
|
|
|
|
|
flash_attn_f16.cl
|
|
|
|
|
flash_attn_f32.cl
|
|
|
|
|
flash_attn_f32_f16.cl
|
|
|
|
|
gelu.cl
|
|
|
|
|
gemm_moe_mxfp4_f32.cl
|
|
|
|
|
gemm_noshuffle_q4_1_f32.cl
|
|
|
|
|
gemm_noshuffle_q6_k_f32.cl
|
|
|
|
|
gemv_moe_mxfp4_f32.cl
|
|
|
|
|
gemv_noshuffle.cl
|
|
|
|
|
gemv_noshuffle_general.cl
|
|
|
|
|
gemv_noshuffle_general_q8_0_f32.cl
|
|
|
|
|
gemv_noshuffle_q4_1_f32.cl
|
|
|
|
|
gemv_noshuffle_q6_k_f32.cl
|
|
|
|
|
get_rows.cl
|
|
|
|
|
glu.cl
|
|
|
|
|
group_norm.cl
|
|
|
|
|
im2col_f16.cl
|
|
|
|
|
im2col_f32.cl
|
|
|
|
|
l2_norm.cl
|
|
|
|
|
mean.cl
|
|
|
|
|
mul.cl
|
|
|
|
|
mul_mat_Ab_Bi_8x4.cl
|
|
|
|
|
mul_mat_f16_f32.cl
|
|
|
|
|
mul_mm_f16_f32_kq_kqv.cl
|
|
|
|
|
mul_mm_f16_f32_l4_lm.cl
|
|
|
|
|
mul_mm_f32_f32_l4_lm.cl
|
|
|
|
|
mul_mm_q4_0_f32_l4_lm.cl
|
|
|
|
|
mul_mm_q4_1_f32_l4_lm.cl
|
|
|
|
|
mul_mm_q4_k_f32_l4_lm.cl
|
|
|
|
|
mul_mm_q6_k_f32_l4_lm.cl
|
|
|
|
|
mul_mm_q8_0_f32_8x4.cl
|
|
|
|
|
mul_mm_q8_0_f32_l4_lm.cl
|
|
|
|
|
mul_mv_f16_f16.cl
|
|
|
|
|
mul_mv_f16_f32.cl
|
|
|
|
|
mul_mv_f16_f32_1row.cl
|
|
|
|
|
mul_mv_f16_f32_l4.cl
|
|
|
|
|
mul_mv_f32_f32.cl
|
|
|
|
|
mul_mv_id_mxfp4_f32.cl
|
|
|
|
|
mul_mv_id_mxfp4_f32_flat.cl
|
|
|
|
|
mul_mv_id_q4_0_f32_8x_flat.cl
|
|
|
|
|
mul_mv_id_q8_0_f32.cl
|
|
|
|
|
mul_mv_id_q8_0_f32_flat.cl
|
|
|
|
|
mul_mv_mxfp4_f32.cl
|
|
|
|
|
mul_mv_mxfp4_f32_flat.cl
|
|
|
|
|
mul_mv_q4_0_f32.cl
|
|
|
|
|
mul_mv_q4_0_f32_1d_16x_flat.cl
|
|
|
|
|
mul_mv_q4_0_f32_1d_8x_flat.cl
|
|
|
|
|
mul_mv_q4_0_f32_8x_flat.cl
|
|
|
|
|
mul_mv_q4_0_f32_v.cl
|
|
|
|
|
mul_mv_q4_1_f32.cl
|
|
|
|
|
mul_mv_q4_1_f32_flat.cl
|
|
|
|
|
mul_mv_q4_k_f32.cl
|
|
|
|
|
mul_mv_q4_k_f32_flat.cl
|
|
|
|
|
mul_mv_q6_k_f32.cl
|
|
|
|
|
mul_mv_q6_k_f32_flat.cl
|
|
|
|
|
mul_mv_q8_0_f32.cl
|
|
|
|
|
mul_mv_q8_0_f32_flat.cl
|
|
|
|
|
neg.cl
|
|
|
|
|
norm.cl
|
|
|
|
|
pad.cl
|
|
|
|
|
relu.cl
|
|
|
|
|
repeat.cl
|
|
|
|
|
rms_norm.cl
|
|
|
|
|
rope.cl
|
|
|
|
|
scale.cl
|
|
|
|
|
set_rows.cl
|
|
|
|
|
sigmoid.cl
|
|
|
|
|
silu.cl
|
|
|
|
|
softmax_4_f16.cl
|
|
|
|
|
softmax_4_f32.cl
|
|
|
|
|
softmax_f16.cl
|
|
|
|
|
softmax_f32.cl
|
|
|
|
|
softplus.cl
|
|
|
|
|
solve_tri.cl
|
|
|
|
|
sqr.cl
|
|
|
|
|
sqrt.cl
|
|
|
|
|
ssm_conv.cl
|
|
|
|
|
sub.cl
|
|
|
|
|
sum_rows.cl
|
|
|
|
|
tanh.cl
|
|
|
|
|
transpose.cl
|
|
|
|
|
tri.cl
|
|
|
|
|
tsembd.cl
|
|
|
|
|
upscale.cl
|
|
|
|