Commit Graph

200 Commits

Author SHA1 Message Date
Aaron Teo
827fce9cf8 Revert "ggml-cpu: move ggml_table_f32_f16 back to ggml-base due to ci failures"
This reverts commit 32a3533564.

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-25 17:00:18 +08:00
Aaron Teo
32a3533564 ggml-cpu: move ggml_table_f32_f16 back to ggml-base due to ci failures
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-25 16:37:48 +08:00
Aaron Teo
9e40d984ad ggml: move ggml_table_f32_f16 to ggml-cpu
ref: https://github.com/ggml-org/llama.cpp/pull/14317#discussion_r2164775006

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-25 14:58:25 +08:00
Aaron Teo
1b23fec005 ggml-cpu: remove mistaken fallback macro
fallback logic was already implemented but i was too sleepy to realise

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-25 01:31:53 +08:00
Aaron Teo
a02b360f2c ggml-cpu: rename all fp16<->fp32 macros to prefix with ggml_cpu
ref: https://github.com/ggml-org/llama.cpp/pull/14317#discussion_r2164449406

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-25 01:07:58 +08:00
Aaron Teo
e4a7f84d37 ggml-cpu: move nnpa together with other fp16<->fp32 simd
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 22:31:39 +08:00
Aaron Teo
e4666f93d3 ggml-cpu: attempt at fixing loongarch failing build
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 22:29:08 +08:00
Aaron Teo
3c055a421e ggml-cpu: fix amx mmq missing simd-mappings.h
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 22:27:11 +08:00
Aaron Teo
e615f73b02 ggml-cpu: fix missing simd-mappings.h within repack
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 21:29:15 +08:00
Aaron Teo
0367b803e9 ggml-cpu: fix missing simd-mappings.h import in quants.c
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 21:09:47 +08:00
Aaron Teo
17b032fab8 ggml: refactor fp16<->fp32 simd to ggml-cpu
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 20:42:15 +08:00
Aaron Teo
8a5e011cb5 Revert "ggml: refactor fp32->fp16 and fp16->fp32 simd to ggml-cpu"
This reverts commit bd288e8fa5.

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 15:54:33 +08:00
Aaron Teo
e73413bb98 Revert "ggml-cpu: fix duplicate func names during compile"
This reverts commit fbb733451f.

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 15:54:18 +08:00
Aaron Teo
fbb733451f ggml-cpu: fix duplicate func names during compile
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-24 15:18:20 +08:00
Aaron Teo
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
Aaron Teo
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
Aaron Teo
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
Aaron Teo
489cdf44bf ggml-cpu: clarify naming of dlf16
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 23:34:42 +08:00
Aaron Teo
46227c61c9 ggml-cpu: remove typedef from cmakelists
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 21:02:05 +08:00
Aaron Teo
1b4dbf477c ggml-cpu: remove typedefs.h
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 21:01:21 +08:00
Aaron Teo
5c9b083511 Revert "ggml-cpu: move s390x typedef to own header file"
This reverts commit 18d79e1a30.

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 20:59:04 +08:00
Aaron Teo
e43dc82a21 ggml-cpu: undo cmakelists work
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 20:56:46 +08:00
Aaron Teo
c8b3b89548 ggml-cpu: add compiler error macro
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 20:17:21 +08:00
Aaron Teo
781c263722 ggml-cpu: move things around
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:41:01 +08:00
Aaron Teo
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
Aaron Teo
1cacdd9a36 ggml-cpu: fix macro declaration
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:08:48 +08:00
Aaron Teo
48df977079 Revert "ggml-cpu: move s390x typedef to own header file"
This reverts commit 157f856c34.

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 19:03:09 +08:00
Aaron Teo
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
Aaron Teo
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
Aaron Teo
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
Aaron Teo
987d1690e4 ggml-cpu: clarified vector naming
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:39:35 +08:00
Aaron Teo
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
Aaron Teo
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
Aaron Teo
7413dabc8c ggml-cpu: fix compiler types
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:23:18 +08:00
Aaron Teo
e12e9fe704 ggml-cpu: reattempt fp32->fp16
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:20:20 +08:00
Aaron Teo
54811fc128 ggml-cpu: fix typo
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:13:57 +08:00
Aaron Teo
433d587426 ggml-cpu: reattempt fp32->fp16
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:12:22 +08:00
Aaron Teo
946c78ebde ggml-cpu: switch to elif macro
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 17:06:18 +08:00
Aaron Teo
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
Aaron Teo
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
Aaron Teo
5424d9e757 ggml-cpu: add breakpoint for debugging
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:51:05 +08:00
Aaron Teo
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
Aaron Teo
e0f8fb930b ggml-cpu: clarify variable naming
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:43:41 +08:00
Aaron Teo
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
Aaron Teo
8312adc980 ggml-cpu: rework noop
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-06-21 16:24:32 +08:00
Aaron Teo
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
Aaron Teo
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
Aaron Teo
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
Aaron Teo
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
Aaron Teo
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