|
Up
|
|
|
|
|
feature-tests/
|
— |
|
|
|
abs.comp
|
|
|
|
|
acc.comp
|
|
|
|
|
add.comp
|
|
|
|
|
add1.comp
|
|
|
|
|
add_id.comp
|
|
|
|
|
arange.comp
|
|
|
|
|
argmax.comp
|
|
|
|
|
argsort.comp
|
|
|
|
|
argsort_large.comp
|
|
|
|
|
ceil.comp
|
|
|
|
|
clamp.comp
|
|
|
|
|
CMakeLists.txt
|
|
|
|
|
concat.comp
|
|
|
|
|
contig_copy.comp
|
|
|
|
|
conv2d_dw.comp
|
|
|
|
|
conv2d_mm.comp
|
|
|
|
|
conv_transpose_1d.comp
|
|
|
|
|
copy.comp
|
|
|
|
|
copy_from_quant.comp
|
|
|
|
|
copy_to_quant.comp
|
|
|
|
|
copy_transpose.comp
|
|
|
|
|
cos.comp
|
|
|
|
|
count_equal.comp
|
|
|
|
|
count_experts.comp
|
|
|
|
|
cumsum.comp
|
|
|
|
|
cumsum_multipass1.comp
|
|
|
|
|
cumsum_multipass2.comp
|
|
|
|
|
dequant_f32.comp
|
|
|
|
|
dequant_funcs.glsl
|
|
|
|
|
dequant_funcs_cm2.glsl
|
|
|
|
|
dequant_head.glsl
|
|
|
|
|
dequant_iq1_m.comp
|
|
|
|
|
dequant_iq1_s.comp
|
|
|
|
|
dequant_iq2_s.comp
|
|
|
|
|
dequant_iq2_xs.comp
|
|
|
|
|
dequant_iq2_xxs.comp
|
|
|
|
|
dequant_iq3_s.comp
|
|
|
|
|
dequant_iq3_xxs.comp
|
|
|
|
|
dequant_iq4_nl.comp
|
|
|
|
|
dequant_iq4_xs.comp
|
|
|
|
|
dequant_mxfp4.comp
|
|
|
|
|
dequant_q2_k.comp
|
|
|
|
|
dequant_q3_k.comp
|
|
|
|
|
dequant_q4_0.comp
|
|
|
|
|
dequant_q4_1.comp
|
|
|
|
|
dequant_q4_k.comp
|
|
|
|
|
dequant_q5_0.comp
|
|
|
|
|
dequant_q5_1.comp
|
|
|
|
|
dequant_q5_k.comp
|
|
|
|
|
dequant_q6_k.comp
|
|
|
|
|
dequant_q8_0.comp
|
|
|
|
|
diag.comp
|
|
|
|
|
diag_mask_inf.comp
|
|
|
|
|
div.comp
|
|
|
|
|
elu.comp
|
|
|
|
|
exp.comp
|
|
|
|
|
fill.comp
|
|
|
|
|
flash_attn.comp
|
|
|
|
|
flash_attn_base.glsl
|
|
|
|
|
flash_attn_cm1.comp
|
|
|
|
|
flash_attn_cm2.comp
|
|
|
|
|
flash_attn_mask_opt.comp
|
|
|
|
|
flash_attn_split_k_reduce.comp
|
|
|
|
|
floor.comp
|
|
|
|
|
gated_delta_net.comp
|
|
|
|
|
geglu.comp
|
|
|
|
|
geglu_erf.comp
|
|
|
|
|
geglu_quick.comp
|
|
|
|
|
gelu.comp
|
|
|
|
|
gelu_erf.comp
|
|
|
|
|
gelu_quick.comp
|
|
|
|
|
generic_binary_head.glsl
|
|
|
|
|
generic_head.glsl
|
|
|
|
|
generic_unary_head.glsl
|
|
|
|
|
get_rows.comp
|
|
|
|
|
get_rows_quant.comp
|
|
|
|
|
glu_head.glsl
|
|
|
|
|
glu_main.glsl
|
|
|
|
|
group_norm.comp
|
|
|
|
|
hardsigmoid.comp
|
|
|
|
|
hardswish.comp
|
|
|
|
|
im2col.comp
|
|
|
|
|
im2col_3d.comp
|
|
|
|
|
l2_norm.comp
|
|
|
|
|
leaky_relu.comp
|
|
|
|
|
log.comp
|
|
|
|
|
mul.comp
|
|
|
|
|
mul_mat_split_k_reduce.comp
|
|
|
|
|
mul_mat_vec.comp
|
|
|
|
|
mul_mat_vec_base.glsl
|
|
|
|
|
mul_mat_vec_iface.glsl
|
|
|
|
|
mul_mat_vec_iq1_m.comp
|
|
|
|
|
mul_mat_vec_iq1_s.comp
|
|
|
|
|
mul_mat_vec_iq2_s.comp
|
|
|
|
|
mul_mat_vec_iq2_xs.comp
|
|
|
|
|
mul_mat_vec_iq2_xxs.comp
|
|
|
|
|
mul_mat_vec_iq3_s.comp
|
|
|
|
|
mul_mat_vec_iq3_xxs.comp
|
|
|
|
|
mul_mat_vec_nc.comp
|
|
|
|
|
mul_mat_vec_p021.comp
|
|
|
|
|
mul_mat_vec_q2_k.comp
|
|
|
|
|
mul_mat_vec_q3_k.comp
|
|
|
|
|
mul_mat_vec_q4_k.comp
|
|
|
|
|
mul_mat_vec_q5_k.comp
|
|
|
|
|
mul_mat_vec_q6_k.comp
|
|
|
|
|
mul_mat_vecq.comp
|
|
|
|
|
mul_mat_vecq_funcs.glsl
|
|
|
|
|
mul_mm.comp
|
|
|
|
|
mul_mm_cm2.comp
|
|
|
|
|
mul_mm_funcs.glsl
|
|
|
|
|
mul_mm_id_funcs.glsl
|
|
|
|
|
mul_mmq.comp
|
|
|
|
|
mul_mmq_funcs.glsl
|
|
|
|
|
mul_mmq_shmem_types.glsl
|
|
|
|
|
multi_add.comp
|
|
|
|
|
neg.comp
|
|
|
|
|
norm.comp
|
|
|
|
|
opt_step_adamw.comp
|
|
|
|
|
opt_step_sgd.comp
|
|
|
|
|
pad.comp
|
|
|
|
|
pool2d.comp
|
|
|
|
|
quantize_q8_1.comp
|
|
|
|
|
reglu.comp
|
|
|
|
|
relu.comp
|
|
|
|
|
repeat.comp
|
|
|
|
|
repeat_back.comp
|
|
|
|
|
rms_norm.comp
|
|
|
|
|
rms_norm_back.comp
|
|
|
|
|
rms_norm_partials.comp
|
|
|
|
|
roll.comp
|
|
|
|
|
rope_funcs.glsl
|
|
|
|
|
rope_head.glsl
|
|
|
|
|
rope_multi.comp
|
|
|
|
|
rope_neox.comp
|
|
|
|
|
rope_norm.comp
|
|
|
|
|
rope_params.glsl
|
|
|
|
|
rope_vision.comp
|
|
|
|
|
round.comp
|
|
|
|
|
rte.glsl
|
|
|
|
|
scale.comp
|
|
|
|
|
sgn.comp
|
|
|
|
|
sigmoid.comp
|
|
|
|
|
silu.comp
|
|
|
|
|
silu_back.comp
|
|
|
|
|
sin.comp
|
|
|
|
|
soft_max.comp
|
|
|
|
|
soft_max_back.comp
|
|
|
|
|
soft_max_large1.comp
|
|
|
|
|
soft_max_large2.comp
|
|
|
|
|
soft_max_large3.comp
|
|
|
|
|
soft_max_large_common.glsl
|
|
|
|
|
softplus.comp
|
|
|
|
|
solve_tri.comp
|
|
|
|
|
sqrt.comp
|
|
|
|
|
square.comp
|
|
|
|
|
ssm_conv.comp
|
|
|
|
|
ssm_scan.comp
|
|
|
|
|
step.comp
|
|
|
|
|
sub.comp
|
|
|
|
|
sum_rows.comp
|
|
|
|
|
sum_rows.glsl
|
|
|
|
|
swiglu.comp
|
|
|
|
|
swiglu_oai.comp
|
|
|
|
|
tanh.comp
|
|
|
|
|
timestep_embedding.comp
|
|
|
|
|
topk_argsort.comp
|
|
|
|
|
topk_moe.comp
|
|
|
|
|
topk_nary_search.comp
|
|
|
|
|
tri.comp
|
|
|
|
|
trunc.comp
|
|
|
|
|
types.glsl
|
|
|
|
|
upscale.comp
|
|
|
|
|
utils.glsl
|
|
|
|
|
vulkan-shaders-gen.cpp
|
|
|
|
|
wkv6.comp
|
|
|
|
|
wkv7.comp
|
|
|
|
|
xielu.comp
|
|
|
|