nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ik_llama_opt/ggml/src/vulkan-shaders
History
Kawrakow 0ceeb11721 Merge mainline llama.cpp (#3) 
* Merging mainline - WIP

* Merging mainline - WIP

AVX2 and CUDA appear to work.
CUDA performance seems slightly (~1-2%) lower as it is so often
the case with llama.cpp/ggml after some "improvements" have been made.

* Merging mainline - fix Metal

* Remove check

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
 		2024-07-27 07:55:01 +02:00
..
CMakeLists.txt Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
add.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
argsort.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
clamp.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
copy.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_f32.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_funcs.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_head.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_iq4_nl.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q2_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q3_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q4_0.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q4_1.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q4_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q5_0.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q5_1.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q5_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q6_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
dequant_q8_0.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
diag_mask_inf.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
div.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
gelu.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
generic_binary_head.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
generic_head.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
generic_unary_head.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
get_rows.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
get_rows_quant.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_split_k_reduce.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_base.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_nc.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_p021.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_q2_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_q3_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_q4_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_q5_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mat_vec_q6_k.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
mul_mm.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
norm.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
relu.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
rms_norm.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
rope_head.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
rope_neox.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
rope_norm.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
scale.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
silu.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
soft_max.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
square.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
sum_rows.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
types.comp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
vulkan-shaders-gen.cpp Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00