klosax
e7a741695c
convert-gptneox-h5-to-gguf.py : Special tokens
2023-08-01 14:30:00 +02:00
ebraminio
86aeb27734
server : Support dark mode ( #2414 )
...
* server : Support dark mode
So it respects user system light / dark settings.
* Update index.html.hpp by running ./deps.sh
2023-08-01 10:56:23 +02:00
Matteo Boschini
1873ff586b
metal : add gqa8 kernel to allow llama-2-70B on metal ( #2459 )
...
* Added gqa8 kernel to allow llama-2-70B on metal
* Update ggml-metal.m
Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
* Extend kernel_mul_mat_f16_f32 to handle gqa broadcast
* Added ne03==ne13 assertion
---------
Co-authored-by: Cebtenzzre <cebtenzzre@gmail.com>
2023-08-01 10:43:12 +03:00
klosax
da4900e835
Update convert-llama-h5-to-gguf.py
2023-07-31 23:04:03 +02:00
M. Yusuf Sarıgöz
f3de876a12
fix : update convert-llama-h5-to-gguf.py
2023-07-31 23:58:29 +03:00
Johannes Gäßler
49e7cb5bb1
CUDA: fixed LLAMA_FAST compilation option ( #2473 )
2023-07-31 21:02:19 +02:00
Johannes Gäßler
b772bba42e
CUDA: fixed cmake F16 option ( #2471 )
2023-07-31 19:52:22 +02:00
M. Yusuf Sarıgöz
bb42aefaeb
gguf : mmap tensor data example
2023-07-31 17:46:12 +03:00
Johannes Gäßler
0728c5a8b9
CUDA: mmq CLI option, fixed mmq build issues ( #2453 )
2023-07-31 15:44:35 +02:00
M. Yusuf Sarıgöz
b26f5b2e43
gguf : fix typo in function call
2023-07-31 16:23:54 +03:00
Johannes Gäßler
1215ed7d5c
CUDA: Implemented row flattening for non-glm RoPE ( #2468 )
2023-07-31 14:32:30 +02:00
Johannes Gäßler
2dbf518911
CUDA: fewer memory bank conflicts for mul_mat_q ( #2458 )
2023-07-31 13:18:51 +02:00
slaren
9d2382b3e4
Fix Metal backend broken from the allocator changes ( #2455 )
...
* fix Metal backend broken from the allocator changes
2023-07-31 11:02:53 +02:00
M. Yusuf Sarıgöz
7aa0a0e7f7
gguf : support custom alignment value
2023-07-31 09:59:36 +03:00
klosax
6b3a7b9f4f
Update convert-llama-h5-to-gguf.py
2023-07-31 03:02:00 +02:00
klosax
4f5b6224be
Update convert-gptneox-h5-to-gguf.py
2023-07-31 03:00:20 +02:00
klosax
2a0914673c
Update convert-gptneox-h5-to-gguf.py
2023-07-30 17:31:11 +02:00
klosax
068a8e0fbe
Update convert-llama-h5-to-gguf.py
2023-07-30 17:29:56 +02:00
klosax
30c4ea47e6
add gptneox gguf example
2023-07-30 16:59:26 +02:00
klosax
2fabc176ce
Update convert-llama-h5-to-gguf.py
2023-07-30 16:28:08 +02:00
slaren
a113689571
ggml : add graph tensor allocator ( #2411 )
...
* ggml : add graph tensor allocator
* ggml : don't calculate data pointer of unallocated tensors when creating a view with an offset
* ggml : refactor ggml_view_Nd into ggml_view_tensor_offset
2023-07-30 15:58:01 +02:00
klosax
f175b05872
Makefile : add gptneox gguf example
2023-07-30 15:08:37 +02:00
klosax
e9192b0135
add gptneox gguf example
2023-07-30 15:05:37 +02:00
klosax
4ed98bf1ab
Update convert-llama-h5-to-gguf.py
2023-07-30 15:01:47 +02:00
klosax
b19c11750b
ggml.c : add gguf_get_arr_n
2023-07-30 14:58:50 +02:00
klosax
b4676ee447
ggml.h : increase GGML_MAX_NAME to 64
2023-07-30 14:51:37 +02:00
klosax
ccd81a751b
gguf.py : add layer norm eps and merges
2023-07-30 14:48:14 +02:00
klosax
0790c121aa
constants.py : add layer norm eps
2023-07-30 14:46:36 +02:00
M. Yusuf Sarıgöz
87c34e4dd4
gguf : update convert-llama-h5-to-gguf.py
2023-07-30 01:09:22 +03:00
M. Yusuf Sarıgöz
32e037ffbe
gguf : fix set is not subscriptable
2023-07-30 01:01:13 +03:00
Johannes Gäßler
11f3ca06b8
CUDA: Quantized matrix matrix multiplication ( #2160 )
...
* mmq implementation for non k-quants
* q6_K
* q2_K
* q3_k
* q4_K
* vdr
* q5_K
* faster q8_1 loading
* loop unrolling
* add __restrict__
* q2_K sc_high
* GGML_CUDA_MMQ_Y
* Updated Makefile
* Update Makefile
* DMMV_F16 -> F16
* Updated README, CMakeLists
* Fix CMakeLists.txt
* Fix CMakeLists.txt
* Fix multi GPU out-of-bounds
2023-07-29 23:04:44 +02:00
Johannes Gäßler
9baf9ef304
CUDA: faster multi GPU synchronization ( #2448 )
2023-07-29 23:04:10 +02:00
klosax
06c3e4a1a7
Update convert-llama-h5-to-gguf.py
2023-07-29 21:38:01 +02:00
klosax
9577821487
gguf.py : support any type
2023-07-29 21:29:07 +02:00
klosax
2c22e3bcdb
ggml.c : get arr str and f32
2023-07-29 20:37:47 +02:00
klosax
34469b9ea7
ggml.h : get array str and f32
2023-07-29 20:36:06 +02:00
M. Yusuf Sarıgöz
0f5e57f01d
gguf : handle already encoded string
2023-07-29 19:56:06 +03:00
klosax
8ad7cd49fb
Update convert-llama-h5-to-gguf.py
2023-07-29 16:47:00 +02:00
M. Yusuf Sarıgöz
0317c41d98
gguf : upd gguf conversion script
2023-07-29 13:31:07 +03:00
M. Yusuf Sarıgöz
cc3dd7f042
gguf : write tokenizer data
2023-07-29 13:30:22 +03:00
M. Yusuf Sarıgöz
8a76dd8a85
gguf : write tensors one by one
2023-07-29 13:17:28 +03:00
M. Yusuf Sarıgöz
c861e234f4
gguf : write tensors one by one
2023-07-29 12:49:01 +03:00
M. Yusuf Sarıgöz
0c219fb5b5
gguf : fix writing gguf arrays
2023-07-29 12:42:54 +03:00
M. Yusuf Sarıgöz
93f7f7aef7
gguf : write tensors one by one and code reuse
2023-07-29 12:34:35 +03:00
M. Yusuf Sarıgöz
aa99562d70
Merge branch 'gguf' of https://github.com//ggerganov/llama.cpp into gguf
2023-07-29 12:26:11 +03:00
M. Yusuf Sarıgöz
ea5f9ad2ca
gguf : fix writing gguf arrays
2023-07-29 12:25:43 +03:00
klosax
999431c4b6
quick and dirty conversion example
2023-07-29 11:20:05 +02:00
M. Yusuf Sarıgöz
d54f53ca51
gguf : add tokenization constants
2023-07-29 12:04:45 +03:00
M. Yusuf Sarıgöz
06f423a8e1
gguf : write sample tensors to read
2023-07-29 10:26:26 +03:00
M. Yusuf Sarıgöz
08dc8fd884
gguf : do not hardcode tensor names to read
2023-07-29 10:24:46 +03:00
