ba3513e44b
ggml-cpu: switch to private macros
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:27:55 +08:00
a91c3ab6b0
ggml-cpu: add ggml-impl.h to cmakelists
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:19:11 +08:00
72c91436f6
ggml-cpu: move macro definitions
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:16:40 +08:00
84593387a7
ggml-cpu: bruteforce macro definitions
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:14:31 +08:00
ed76ff6e42
ggml-cpu: add debug prints
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:11:59 +08:00
fadc138763
ggml-cpu: test more macros
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:10:39 +08:00
1cacdd9a36
ggml-cpu: fix macro declaration
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:08:48 +08:00
3004a79f4b
ggml-cpu: switch to importing ggml-cpu-impl instead
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:04:09 +08:00
48df977079
Revert "ggml-cpu: move s390x typedef to own header file"
...
This reverts commit 157f856c34
2025-06-21 19:03:09 +08:00
157f856c34
ggml-cpu: move s390x typedef to own header file
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:00:20 +08:00
e7910fc975
ggml-cpu: update macro tests
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 18:43:43 +08:00
8129838037
ggml-cpu: import vecintrin.h to fix compiler errors
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 18:42:02 +08:00
4ad6efa37b
ggml-cpu: diagnose why __NNPA__ macro is not being defined
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 18:33:08 +08:00
0e571dd3d8
ggml-cpu: add missing __func__
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 18:10:26 +08:00
1547ea230c
ggml-cpu: add nnpa macro check in ggml-impl
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 18:09:37 +08:00
f1b1d98e8d
ggml-cpu: activate nnpa fp32->fp16 or fp16->fp32 compute
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:51:55 +08:00
8ef51b9055
ggml-cpu: bring back fp32->fp16 store nnpa
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:49:36 +08:00
987d1690e4
ggml-cpu: clarified vector naming
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:39:35 +08:00
4621a23c14
ggml-cpu: add 4 element loops for fp32->fp16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:32:20 +08:00
373fa28e4c
ggml-cpu: change to typedef vector types
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:26:20 +08:00
7413dabc8c
ggml-cpu: fix compiler types
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:23:18 +08:00
e12e9fe704
ggml-cpu: reattempt fp32->fp16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:20:20 +08:00
54811fc128
ggml-cpu: fix typo
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:13:57 +08:00
433d587426
ggml-cpu: reattempt fp32->fp16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:12:22 +08:00
946c78ebde
ggml-cpu: switch to elif macro
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:06:18 +08:00
27131e5f34
ggml-cpu: disable fp32->fp16 nnpa conversions for now
...
there are some conversion failures in nnpa that requires the eyes of an
ibm stsm. will create a separate pr to introduce the fp32->fp16 change.
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:58:43 +08:00
4f017d718a
ggml-cpu: test fix for conversion failure
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:55:16 +08:00
5424d9e757
ggml-cpu: add breakpoint for debugging
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:51:05 +08:00
bb9345ca8a
ggml-cpu: activate nnpa for ggml_cpu_fp32_to_fp16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:50:05 +08:00
e0f8fb930b
ggml-cpu: clarify variable naming
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:43:41 +08:00
27b4c3f338
ggml-cpu: remove noop, general code cleanup
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:41:39 +08:00
8312adc980
ggml-cpu: rework noop
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:24:32 +08:00
6d507bbeb0
ggml-cpu: switch to vec_xst for 4 element loops also
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:23:23 +08:00
f9f6c7e897
ggml-cpu: nnpa switch to vec_xst test
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:16:35 +08:00
6a25fd8531
ggml-cpu: nnpa activate ggml_cpu_fp16_to_fp32 for 8 elements
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:10:44 +08:00
ebc1d19f62
ggml-cpu: activate nnpa for ggml_cpu_fp16_to_fp32
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:01:55 +08:00
9330454cb8
ggml-cpu: remove sigint from fp16 store
...
for some reason, the function is not getting a hit when debugged with
gdb. we will need to investigate further
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 15:06:31 +08:00
575ea9f6c6
ggml-cpu: fp16 load ensured to hit
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 15:00:46 +08:00
8f3a5af6c0
ggml-cpu: ensure fp16 and fp32 load and stores are called
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 14:57:25 +08:00
94f10ca189
ggml-cpu: fix float placeholder
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 14:53:15 +08:00
d9cc63a94a
ggml-cpu: fix print vs printf
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 14:51:38 +08:00
48b820d05f
ggml-cpu: add debugging prints to see if dlf16 is correct
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 14:50:33 +08:00
ffe296457e
ggml-cpu: better variable names
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 2f58bbcbb8
2025-06-21 14:47:46 +08:00
ebf9f34a38
ggml-cpu: add fp32->fp16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 0ff0d65162
2025-06-21 14:47:23 +08:00
45a4cf651c
ggml-cpu: add fp16->fp32 nnpa first
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 8d4a7987f9
2025-06-21 14:47:12 +08:00
5801806f70
ggml-cpu: add nnpa compile flag
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 4a9f60c201
2025-06-21 14:46:41 +08:00
bb16041cae
Add support for VK_EXT_debug_utils to add labels to Vulkan objects. ( #13792 )
...
* Add support for VK_EXT_debug_utils to add labels to Vulkan objects. In step 1 compute pipelines are getting labeled.
* remove #ifdef for debug utils and add queue marker.
2025-06-21 08:17:12 +02:00
67ae5312e2
metal : fix thread-safety ( #14300 )
...
ggml-ci
2025-06-21 08:04:18 +03:00
b7147673f2
Add `ggml_roll` (ggml/1274)
...
* ggml : add ggml_roll
* use set/get_op_params & std::min
2025-06-20 21:02:47 +03:00
c959f462a0
CUDA: add conv_2d_transpose ( #14287 )
...
* CUDA: add conv_2d_transpose
* remove direct include of cuda_fp16
* Review: add brackets for readability, remove ggml_set_param and add asserts
2025-06-20 22:48:24 +08:00
Aaron Teo
Markus Tavenrath
Georgi Gerganov
Acly
Aman Gupta