bd288e8fa5
ggml: refactor fp32->fp16 and fp16->fp32 simd to ggml-cpu
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 15:05:46 +08:00
5834dee1fc
ggml-cpu: move nnpa fp16->fp32 and fp32->fp16 to simd-mappings
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-23 17:52:28 +08:00
5004e4395b
ggml-cpu: remove unnecessary target compile definitions
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 23:37:44 +08:00
489cdf44bf
ggml-cpu: clarify naming of dlf16
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 23:34:42 +08:00
46227c61c9
ggml-cpu: remove typedef from cmakelists
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 21:02:05 +08:00
1b4dbf477c
ggml-cpu: remove typedefs.h
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 21:01:21 +08:00
5c9b083511
Revert "ggml-cpu: move s390x typedef to own header file"
...
This reverts commit 18d79e1a30
2025-06-21 20:59:04 +08:00
e43dc82a21
ggml-cpu: undo cmakelists work
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 20:56:46 +08:00
c8b3b89548
ggml-cpu: add compiler error macro
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 20:17:21 +08:00
781c263722
ggml-cpu: move things around
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:41:01 +08:00
18d79e1a30
ggml-cpu: move s390x typedef to own header file
...
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
(cherry picked from commit 157f856c34
2025-06-21 19:31:34 +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
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
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
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
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
6369be0735
Implement GGML_CPU_ALL_VARIANTS for PowerPC ( #14286 )
...
* Add PowerPC feature detection and scoring
* ggml-cpu: Implement GGML_CPU_ALL_VARIANTS for PowerPC
* ggml-cpu: Delay some initializations until function is called
When using GGML_BACKEND_DL=ON, these initializations might use
instructions that are not supported by the current CPU.
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-06-20 14:17:32 +02:00
d27b3ca175
ggml : fix repack work size for mul_mat_id ( #14292 )
...
ggml-ci
2025-06-20 11:19:15 +03:00
9230dbe2c7
ggml: Update KleidiAI to v1.9.0 ( #14277 )
2025-06-20 10:51:01 +03:00
8f71d0f3e8
ggml-cpu : remove unnecesary arm feature detection ( #14281 )
...
Support for Arm runtime feature detection has now been added to GGML_CPU_ALL_VARIANTS. This removes the old and not very functional code.
2025-06-19 21:24:14 +02:00
Aaron Teo
Acly
Christian Kastner
Georgi Gerganov
Charles Xu
Diego Devesa