Abhilash Majumder
|
f707051066
|
Update CMakeLists.txt
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
2024-01-26 20:49:07 +05:30 |
|
Abhilash Majumder
|
2cba564b49
|
Update examples/sycl/run-llama2.sh
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
2024-01-26 20:48:49 +05:30 |
|
Abhilash Majumder
|
c08fec2a38
|
Update examples/sycl/run-llama2.sh
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
2024-01-26 20:43:17 +05:30 |
|
Abhilash Majumder
|
174c9a0ed6
|
Update ci/run.sh
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
|
2024-01-26 20:40:50 +05:30 |
|
luoyu-intel
|
d6a6505018
|
implement std::isinf for icpx with fast math.
|
2024-01-26 18:31:04 +08:00 |
|
Meng, Hengyu
|
05b7f9be6f
|
revert setting n_threads in sycl
|
2024-01-25 09:44:19 +00:00 |
|
Meng, Hengyu
|
b06dca678b
|
remove extra blank line in test-sampling
|
2024-01-25 09:38:36 +00:00 |
|
Meng, Hengyu
|
66e24c2468
|
pass void as arguments of ggml_backend_sycl_print_sycl_devices
|
2024-01-25 09:26:02 +00:00 |
|
Meng, Hengyu
|
f1bab50100
|
revert sycl checking in test-sampling
|
2024-01-25 09:21:16 +00:00 |
|
luoyu-intel
|
0635f844c9
|
fix wrong code
|
2024-01-24 22:00:24 +08:00 |
|
luoyu-intel
|
5bb93d41b7
|
fix batch error
|
2024-01-24 21:56:47 +08:00 |
|
luoyu-intel
|
eef5faae18
|
pass batch offset for F16 src1
|
2024-01-24 21:46:48 +08:00 |
|
luoyu-intel
|
5600118221
|
fix src1->type==F16 bug.
|
2024-01-24 21:29:21 +08:00 |
|
Meng, Hengyu
|
0e235fb816
|
fix no_new_line
|
2024-01-24 13:26:04 +00:00 |
|
Abhilash Majumder
|
18742f7afc
|
rm cpu blas duplicate
|
2024-01-24 18:14:45 +05:30 |
|
Meng, Hengyu
|
3aabd8a274
|
revert no mmq
|
2024-01-24 12:40:54 +00:00 |
|
jianyuzh
|
8dd1b60ac6
|
add prefix in func name
|
2024-01-24 20:34:55 +08:00 |
|
Meng, Hengyu
|
d07a88d448
|
fix indent
|
2024-01-24 12:32:54 +00:00 |
|
Meng, Hengyu
|
96186a742a
|
revert hip cmake changes
|
2024-01-24 12:23:23 +00:00 |
|
Meng, Hengyu
|
fb15de38ef
|
revert unrelated changed in cuda cmake
remove useless nommq
fix typo of GGML_USE_CLBLAS_SYCL
|
2024-01-24 12:18:30 +00:00 |
|
jianyuzh
|
67de350e79
|
fix ci cases for unsupported data type
|
2024-01-24 19:51:24 +08:00 |
|
Abhilash Majumder
|
238ec31aeb
|
Merge branch 'master' into sycl
|
2024-01-24 15:14:03 +05:30 |
|
jianyuzh
|
22e1b45c02
|
fix build break on MacOS, due to CI of MacOS depend on external ggml, instead of internal ggml
|
2024-01-24 17:24:24 +08:00 |
|
jianyuzh
|
ec5c8bc0c9
|
fix conflict
|
2024-01-24 16:34:41 +08:00 |
|
Meng, Hengyu
|
799af05619
|
enable llama_f16 in ci
|
2024-01-24 07:45:36 +00:00 |
|
jianyuzh
|
04a46c46f8
|
rm unused strategy
|
2024-01-24 14:55:59 +08:00 |
|
jianyuzh
|
7babd76903
|
fix action ID format issue
|
2024-01-24 14:53:04 +08:00 |
|
jianyuzh
|
7a44a95b08
|
update CI/action for sycl code, fix CI error of repeat/dup
|
2024-01-24 14:39:46 +08:00 |
|
jianyuzh
|
816f480e98
|
export funciton print_sycl_devices(), mv class dpct definition to source file
|
2024-01-24 10:10:45 +08:00 |
|
jianyuzh
|
91b1461030
|
mv internal function to .cpp file
|
2024-01-24 09:41:25 +08:00 |
|
jianyuzh
|
498121b11f
|
ren as review comments
|
2024-01-24 09:20:42 +08:00 |
|
jianyuzh
|
3bfb846d6a
|
fix conflict
|
2024-01-23 23:45:56 +08:00 |
|
abhilash1910
|
c7e745e6f3
|
restore hip dependency
|
2024-01-23 07:35:31 -08:00 |
|
abhilash1910
|
d6fc1a0309
|
fix mac build
|
2024-01-23 07:19:30 -08:00 |
|
Georgi Gerganov
|
26d607608d
|
metal : disable support for MUL_MAT F32 x F16
|
2024-01-23 15:50:56 +02:00 |
|
Kawrakow
|
44879ee885
|
Additional KL-divergence statistics (#5081)
* perplexity: add top-token probability
* perplexity: add additional KL-divergence statistics
* perplexity: a better organized KL-divergence statistics output
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
|
2024-01-23 15:17:20 +02:00 |
|
Johannes Gäßler
|
9ecdd12e95
|
CUDA: more info when no device code (#5088)
|
2024-01-23 13:31:56 +01:00 |
|
Abhilash Majumder
|
5f83a12382
|
fix blas matmul function
|
2024-01-23 17:56:37 +05:30 |
|
jianyuzh
|
b42a32d31a
|
replace tab by space
|
2024-01-23 20:20:16 +08:00 |
|
Georgi Gerganov
|
89758723c7
|
minor : clean-up some warnings and style (#5094)
* minor : clean-up some warnings and style
ggml-ci
* ggml : add comment
|
2024-01-23 14:12:57 +02:00 |
|
jianyuzh
|
756c4accaf
|
skip build sycl tool for other code path
|
2024-01-23 20:06:20 +08:00 |
|
Abhilash Majumder
|
88f64b7d3d
|
Remove unused headers
|
2024-01-23 17:34:57 +05:30 |
|
Abhilash Majumder
|
d097e2a4ef
|
editor format fix
|
2024-01-23 17:32:42 +05:30 |
|
Abhilash Majumder
|
be31379ef8
|
format fixes
|
2024-01-23 14:47:30 +05:30 |
|
Abhilash Majumder
|
bd716b2594
|
format fixes
|
2024-01-23 14:45:36 +05:30 |
|
abhilash1910
|
1ddaf44c30
|
editor config format
|
2024-01-23 01:03:34 -08:00 |
|
Xuan Son Nguyen
|
2bed4aa3f3
|
devops : add intel oneapi dockerfile (#5068)
Co-authored-by: Xuan Son Nguyen <xuanson.nguyen@snowpack.eu>
|
2024-01-23 09:11:39 +02:00 |
|
Michael Coppola
|
125d03a503
|
llama.vim : added api key support (#5090)
Co-authored-by: Michael Coppola <info@michaeljcoppola.com>
|
2024-01-23 08:51:27 +02:00 |
|
jianyuzh
|
97cbe18dd2
|
rename macro to intel hardware
|
2024-01-23 14:35:33 +08:00 |
|
jianyuzh
|
27c08c0429
|
Merge branch 'sycl' of https://github.com/abhilash1910/llama.cpp into sycl
|
2024-01-23 14:16:24 +08:00 |
|