vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-05 20:19:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
kvcache-ai-ktransformers/third_party/llamafile
History
chenxl 1db4a67dca [feature] add github action for pre compile
2024-08-14 16:54:50 +00:00
..
bench.h Initial commit 2024-07-27 16:06:58 +08:00
flags.cpp Initial commit 2024-07-27 16:06:58 +08:00
flags.h Initial commit 2024-07-27 16:06:58 +08:00
iqk_mul_mat.inc [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
iqk_mul_mat_amd_avx2.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
iqk_mul_mat_amd_zen4.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
iqk_mul_mat_arm82.cpp Initial commit 2024-07-27 16:06:58 +08:00
macros.h Initial commit 2024-07-27 16:06:58 +08:00
micros.h Initial commit 2024-07-27 16:06:58 +08:00
numba.h Initial commit 2024-07-27 16:06:58 +08:00
README.md Initial commit 2024-07-27 16:06:58 +08:00
sgemm.cpp [feature] add github action for pre compile 2024-08-14 16:54:50 +00:00
sgemm.h Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu.h [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul.inc Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu_mixmul_amd_avx.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_amd_avx2.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_amd_avx512f.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_amd_avxvnni.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_amd_fma.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_amd_zen4.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_mixmul_arm80.cpp Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu_mixmul_arm82.cpp Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu_sgemm.inc [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_avx.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_avx2.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_avx512f.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_avxvnni.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_fma.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_amd_zen4.cpp [ADD] support multi-gpu qlen>1 q5_k 2024-08-12 11:41:26 +00:00
tinyblas_cpu_sgemm_arm80.cpp Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu_sgemm_arm82.cpp Initial commit 2024-07-27 16:06:58 +08:00
tinyblas_cpu_unsupported.cpp Initial commit 2024-07-27 16:06:58 +08:00

README.md

The code in this folder is copied from Mozilla-Ocho/llamafile. Special thanks to the Mozilla-Ocho team.