| .. |
|
tools
|
Merge branch 'master' into concedo_experimental
|
2024-02-28 13:41:35 +08:00 |
|
ggml_v1.c
|
Merge branch 'master' into concedo_experimental
|
2023-10-31 20:44:04 +08:00 |
|
ggml_v1.h
|
Various enhancement and integration pygmalion.cpp
|
2023-04-03 00:04:43 +08:00 |
|
ggml_v2-cuda-legacy.cu
|
increase pool buffers
|
2024-01-20 11:52:39 +08:00 |
|
ggml_v2-cuda-legacy.h
|
Wip, CUDA porting malloc improvements, gpu accel for non-llama, backport old quants
|
2023-06-28 18:20:46 +08:00 |
|
ggml_v2-cuda.cu
|
Koboldcpp-ROCm Port (#399)
|
2023-08-28 17:05:06 +08:00 |
|
ggml_v2-cuda.h
|
cleanup indentation, fixing cublas build
|
2023-06-08 22:40:53 +08:00 |
|
ggml_v2-opencl-legacy.c
|
Merge remote-tracking branch 'occam/opencl-dev' into concedo_experimental
|
2023-05-22 16:16:48 +08:00 |
|
ggml_v2-opencl-legacy.h
|
still merging in process
|
2023-05-20 15:58:33 +08:00 |
|
ggml_v2-opencl.cpp
|
Reduce warnings. (#439)
|
2023-09-16 18:52:09 +08:00 |
|
ggml_v2-opencl.h
|
still merging in process
|
2023-05-20 15:58:33 +08:00 |
|
ggml_v2.c
|
Reduce warnings. (#439)
|
2023-09-16 18:52:09 +08:00 |
|
ggml_v2.h
|
remove old filever checks (+7 squashed commit)
|
2023-05-21 00:15:39 +08:00 |
|
ggml_v3-cuda.cu
|
try fix cuda slowdown
|
2024-02-05 16:34:15 +08:00 |
|
ggml_v3-cuda.h
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
ggml_v3-opencl.cpp
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
ggml_v3-opencl.h
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
ggml_v3.c
|
Merge branch 'master' into concedo_experimental
|
2024-01-20 23:27:42 +08:00 |
|
ggml_v3.h
|
try to use allocator for cuda ggml v3
|
2024-01-20 12:53:31 +08:00 |
|
gpt2_v1.cpp
|
fixed other arch
|
2023-05-24 00:20:43 +08:00 |
|
gpt2_v2.cpp
|
Reduce warnings. (#439)
|
2023-09-16 18:52:09 +08:00 |
|
gpt2_v3.cpp
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
gptj_v1.cpp
|
remove old filever checks (+7 squashed commit)
|
2023-05-21 00:15:39 +08:00 |
|
gptj_v2.cpp
|
Reduce warnings. (#439)
|
2023-09-16 18:52:09 +08:00 |
|
gptj_v3.cpp
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
llama-util.h
|
units (+2 squashed commit)
|
2024-01-20 23:53:21 +08:00 |
|
llama_v2-util.h
|
units (+2 squashed commit)
|
2024-01-20 23:53:21 +08:00 |
|
llama_v2.cpp
|
Koboldcpp-ROCm Port (#399)
|
2023-08-28 17:05:06 +08:00 |
|
llama_v2.h
|
still merging in process
|
2023-05-20 15:58:33 +08:00 |
|
llama_v3.cpp
|
refactor identifiers
|
2024-01-20 17:26:11 +08:00 |
|
llama_v3.h
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
mpt_v3.cpp
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
neox_v2.cpp
|
fixed other arch
|
2023-05-24 00:20:43 +08:00 |
|
neox_v3.cpp
|
fossilize ggml library ver 3, to support ggjtv3
|
2024-01-20 10:49:25 +08:00 |
|
otherarch.h
|
try to use allocator for cuda ggml v3
|
2024-01-20 12:53:31 +08:00 |
|
rwkv_v2.cpp
|
Reduce warnings. (#439)
|
2023-09-16 18:52:09 +08:00 |
|
rwkv_v2.h
|
wip integrating new rwkv
|
2023-05-27 22:45:28 +08:00 |
|
rwkv_v3.cpp
|
change listen count, fix null
|
2024-02-16 16:01:24 +08:00 |
|
rwkv_v3.h
|
fix compile errors, rwkv not working
|
2023-07-10 18:23:25 +08:00 |
|
rwkv_vocab.cpp
|
integrated world tokenizer for RWKV
|
2023-06-13 20:06:19 +08:00 |
|
utils.cpp
|
b64 decoder
|
2024-02-11 20:35:34 +08:00 |
|
utils.h
|
b64 decoder
|
2024-02-11 20:35:34 +08:00 |
ad638285de