public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
whisper.cpp/ggml/src/ggml-vulkan/vulkan-shaders
History
Georgi Gerganov 85dcc74b88 sync : resolve conflicts (ggml/0) 
ggml-ci
 		2025-07-12 19:23:56 +03:00
..
CMakeLists.txt vulkan: Fix GGML_VULKAN_SHADER_DEBUG_INFO (llama/14427) 2025-07-01 17:54:53 +03:00
acc.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
add.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
argmax.comp vulkan: implement several ops relevant for ggml_opt (llama/11769) 2025-02-27 08:55:36 +02:00
argsort.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
clamp.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
concat.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
contig_copy.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
conv2d_dw.comp vulkan : fix lint (llama/0) 2025-05-07 15:39:32 +03:00
conv_transpose_1d.comp ggml-vulkan: adds support for op CONV_TRANSPOSE_1D (llama/13813) 2025-06-10 12:40:33 +03:00
copy.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
copy_from_quant.comp vulkan: initial support for IQ1_S and IQ1_M quantizations (llama/11528) 2025-02-27 08:55:36 +02:00
copy_to_quant.comp vulkan: support SET_ROWS (llama/14587) 2025-07-12 19:23:56 +03:00
cos.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
count_equal.comp vulkan: implement several ops relevant for ggml_opt (llama/11769) 2025-02-27 08:55:36 +02:00
dequant_f32.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_funcs.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
dequant_funcs_cm2.comp vulkan: use uint array index to avoid glslang bug (llama/13193) 2025-05-01 13:29:02 +03:00
dequant_head.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_iq1_m.comp vulkan: fix warnings (llama/13626) 2025-05-27 18:03:00 +03:00
dequant_iq1_s.comp vulkan: initial support for IQ1_S and IQ1_M quantizations (llama/11528) 2025-02-27 08:55:36 +02:00
dequant_iq2_s.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq2_xs.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq2_xxs.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq3_s.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq3_xxs.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq4_nl.comp vulkan: implement initial support for IQ2 and IQ3 quantizations (llama/11360) 2025-02-03 22:00:57 +02:00
dequant_iq4_xs.comp vulkan: initial support for IQ4_XS quantization (llama/11501) 2025-02-27 08:55:36 +02:00
dequant_q2_k.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q3_k.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q4_0.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q4_1.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q4_k.comp Vulkan: Use improved q4_k and q5_k dequant code in dequant shaders (llama/10798) 2024-12-18 12:52:16 +02:00
dequant_q5_0.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q5_1.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q5_k.comp Vulkan: Use improved q4_k and q5_k dequant code in dequant shaders (llama/10798) 2024-12-18 12:52:16 +02:00
dequant_q6_k.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
dequant_q8_0.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
diag_mask_inf.comp vulkan: fix diag_mask_inf (llama/11323) 2025-02-03 22:00:57 +02:00
div.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
flash_attn.comp vulkan: Handle updated FA dim2/3 definition (llama/14518) 2025-07-12 19:23:56 +03:00
flash_attn_base.comp vulkan: Handle updated FA dim2/3 definition (llama/14518) 2025-07-12 19:23:56 +03:00
flash_attn_cm1.comp vulkan: Handle updated FA dim2/3 definition (llama/14518) 2025-07-12 19:23:56 +03:00
flash_attn_cm2.comp vulkan: Handle updated FA dim2/3 definition (llama/14518) 2025-07-12 19:23:56 +03:00
flash_attn_split_k_reduce.comp vulkan: optimize flash attention split_k_reduce (llama/14554) 2025-07-12 19:23:56 +03:00
geglu.comp ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 2025-07-01 17:54:53 +03:00
geglu_erf.comp ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) 2025-07-12 19:23:56 +03:00
geglu_quick.comp ggml : implement GEGLU_ERF and GEGLU_QUICK ops (llama/14445) 2025-07-12 19:23:56 +03:00
gelu.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
gelu_erf.comp add GELU_ERF (llama/14455) 2025-07-12 19:23:56 +03:00
gelu_quick.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
generic_binary_head.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
generic_head.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
generic_unary_head.comp vulkan: support copy from f32 to q4_0/q4_1/q5_0/q5_1/q8_0/iq4_nl (llama/11166) 2025-02-03 22:00:57 +02:00
get_rows.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
get_rows_quant.comp vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (llama/11595) 2025-03-08 15:13:01 +02:00
glu_head.comp ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 2025-07-01 17:54:53 +03:00
glu_main.comp ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 2025-07-01 17:54:53 +03:00
group_norm.comp vulkan: fix group_norm (llama/10496) 2024-12-08 20:14:35 +02:00
im2col.comp vulkan: improve im2col (llama/11826) 2025-03-08 15:13:01 +02:00
l2_norm.comp llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00
leaky_relu.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
mul.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
mul_mat_split_k_reduce.comp vulkan: optimize and reenable split_k (llama/10637) 2024-12-08 20:14:35 +02:00
mul_mat_vec.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
mul_mat_vec_base.comp vulkan: optimize mul_mat for small values of N (llama/10991) 2025-01-04 10:45:01 +02:00
mul_mat_vec_iq1_m.comp vulkan: initial support for IQ1_S and IQ1_M quantizations (llama/11528) 2025-02-27 08:55:36 +02:00
mul_mat_vec_iq1_s.comp vulkan: initial support for IQ1_S and IQ1_M quantizations (llama/11528) 2025-02-27 08:55:36 +02:00
mul_mat_vec_iq2_s.comp vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (llama/12472) 2025-03-27 11:06:03 +02:00
mul_mat_vec_iq2_xs.comp vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (llama/11595) 2025-03-08 15:13:01 +02:00
mul_mat_vec_iq2_xxs.comp vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (llama/11595) 2025-03-08 15:13:01 +02:00
mul_mat_vec_iq3_s.comp vulkan: workaround for AMD Windows driver 16 bit unpack8 bug (llama/12472) 2025-03-27 11:06:03 +02:00
mul_mat_vec_iq3_xxs.comp vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (llama/11595) 2025-03-08 15:13:01 +02:00
mul_mat_vec_nc.comp vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul shader (llama/13191) 2025-05-07 15:39:32 +03:00
mul_mat_vec_p021.comp vulkan: Optimize mul_mat_vec p021 and nc shaders (llama/12505) 2025-03-27 11:06:03 +02:00
mul_mat_vec_q2_k.comp mat vec double buffer (llama/12188) 2025-03-27 11:06:03 +02:00
mul_mat_vec_q3_k.comp mat vec double buffer (llama/12188) 2025-03-27 11:06:03 +02:00
mul_mat_vec_q4_k.comp vulkan: scale caching for k quants + misc fixes (llama/11081) 2025-02-03 22:00:57 +02:00
mul_mat_vec_q5_k.comp vulkan: scale caching for k quants + misc fixes (llama/11081) 2025-02-03 22:00:57 +02:00
mul_mat_vec_q6_k.comp mat vec double buffer (llama/12188) 2025-03-27 11:06:03 +02:00
mul_mm.comp vulkan: optimizations for deepseek prompt processing (llama/14555) 2025-07-12 19:23:56 +03:00
mul_mm_cm2.comp vulkan: optimizations for deepseek prompt processing (llama/14555) 2025-07-12 19:23:56 +03:00
mul_mmq.comp vulkan: Allow up to 4096 elements for mul_mat_id row_ids (llama/13326) 2025-05-13 13:59:21 +03:00
mul_mmq_funcs.comp Vulkan: Fix mmq int dot float cache size (llama/12722) 2025-04-24 20:39:16 +03:00
norm.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
opt_step_adamw.comp vulkan: implement several ops relevant for ggml_opt (llama/11769) 2025-02-27 08:55:36 +02:00
pad.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
pool2d.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
quantize_q8_1.comp Vulkan: Add DP4A MMQ and Q8_1 quantization shader (llama/12135) 2025-04-02 15:51:57 +03:00
reglu.comp ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 2025-07-01 17:54:53 +03:00
relu.comp vulkan: Additional type support for unary, binary, and copy (llama/13266) 2025-05-07 21:00:32 +03:00
repeat.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
repeat_back.comp vulkan: implement several ops relevant for ggml_opt (llama/11769) 2025-02-27 08:55:36 +02:00
rms_norm.comp vulkan: Add fusion support for RMS_NORM+MUL (llama/14366) 2025-07-01 17:54:53 +03:00
rms_norm_back.comp vulkan : sync (llama/0) 2025-03-08 15:13:01 +02:00
roll.comp vulkan : implement ggml_roll (ggml/1290) 2025-07-12 19:23:56 +03:00
rope_head.comp vulkan : sync (llama/0) 2025-03-08 15:13:01 +02:00
rope_multi.comp vulkan : fix rope with partial rotation and non-cont src (llama/14582) 2025-07-12 19:23:56 +03:00
rope_neox.comp vulkan : fix rope with partial rotation and non-cont src (llama/14582) 2025-07-12 19:23:56 +03:00
rope_norm.comp vulkan : fix rope with partial rotation and non-cont src (llama/14582) 2025-07-12 19:23:56 +03:00
rope_vision.comp vulkan: support multi/vision rope, and noncontiguous rope (llama/11902) 2025-02-27 08:55:36 +02:00
scale.comp ggml : add ggml_scale_bias (llama/14417) 2025-07-12 19:23:56 +03:00
sigmoid.comp vulkan: Additional type support for unary, binary, and copy (llama/13266) 2025-05-07 21:00:32 +03:00
silu.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
silu_back.comp vulkan : sync (llama/0) 2025-03-08 15:13:01 +02:00
sin.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
soft_max.comp vulkan: support softmax/FA batch and broadcast (llama/14449) 2025-07-12 19:23:56 +03:00
soft_max_back.comp vulkan : sync (llama/0) 2025-03-08 15:13:01 +02:00
square.comp vulkan: Use push constant offset to handle misaligned descriptors (llama/10987) 2025-01-04 10:45:01 +02:00
sub.comp vulkan: implement several ops relevant for ggml_opt (llama/11769) 2025-02-27 08:55:36 +02:00
sum_rows.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
swiglu.comp ggml : implement REGLU/GEGLU/SWIGLU ops (llama/14158) 2025-07-01 17:54:53 +03:00
tanh.comp vulkan: Additional type support for unary, binary, and copy (llama/13266) 2025-05-07 21:00:32 +03:00
test_bfloat16_support.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
test_coopmat2_support.comp vulkan: compile a test shader in cmake to check for coopmat2 support (llama/10713) 2024-12-18 12:52:16 +02:00
test_coopmat_support.comp Disable GL_KHR_cooperative_matrix Vulkan extension if not available. (llama/11117) 2025-01-14 10:38:01 +02:00
test_integer_dot_support.comp Vulkan: Add DP4A MMQ and Q8_1 quantization shader (llama/12135) 2025-04-02 15:51:57 +03:00
timestep_embedding.comp ggml : build backends as libraries (llama/10256) 2024-11-20 21:00:08 +02:00
types.comp vulkan: Add bfloat16 support (llama/12554) 2025-05-07 15:39:32 +03:00
upscale.comp sync : resolve conflicts (ggml/0) 2025-07-12 19:23:56 +03:00
vulkan-shaders-gen.cpp sync : resolve conflicts (ggml/0) 2025-07-12 19:23:56 +03:00
wkv6.comp rwkv6: add wkv6 support for Vulkan backend (llama/10829) 2024-12-18 12:52:16 +02:00
wkv7.comp llama: Add support for RWKV v7 architecture (llama/12412) 2025-03-27 11:06:03 +02:00