Commit Graph

6000 Commits

Author SHA1 Message Date
Aaron Teo 92a17ed9f3
ggml-zdnn: clean up project structure
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 17:36:38 +08:00
Aaron Teo 90d460c20b
ggml-zdnn: clean up matmul selection
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 17:34:15 +08:00
Aaron Teo e67feafc65
ggml-zdnn: fix ztensor deallocation abort
stabilise ggml <-> zdnn api

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 17:27:49 +08:00
Aaron Teo 803dde3bbc
ggml-zdnn: code clean up
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 17:23:36 +08:00
Aaron Teo 70224e6cb7
ggml-zdnn: bring load ztensor back to init routine
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 17:21:04 +08:00
Aaron Teo 1eb7c35e3a
ggml-zdnn: code cleanup
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 16:57:14 +08:00
Aaron Teo b7a77cf683
ggml-zdnn: add guards to prevent loading ztensor if transformed
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 16:15:20 +08:00
Aaron Teo 4d5edb2221
ggml-zdnn: fix errorenous output load tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 16:11:07 +08:00
Aaron Teo 20d69b6cdf
ggml-zdnn: disable global load ztensor for now
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 16:05:58 +08:00
Aaron Teo 4fb6bee1f6
ggml-zdnn: attempt at using default nwhc format instead
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 16:04:19 +08:00
Aaron Teo 7b50d057dd
ggml-zdnn: attempt at manually changing the layout
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 15:33:13 +08:00
Aaron Teo ad0cb30212
ggml-zdnn: disable logging and breakpoints for full test
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:52:13 +08:00
Aaron Teo b4dffed954
ggml-zdnn: work on moving output ztensor as well
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:50:09 +08:00
Aaron Teo fd766bdd44
ggml-zdnn: load ztensors in cgraph exec
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:40:36 +08:00
Aaron Teo e30b1ffbde
ggml-zdnn: fix missing return from init_tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:34:47 +08:00
Aaron Teo 4493b148d0
ggml-zdnn: disable op_none initialisation for testing
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:33:12 +08:00
Aaron Teo 213f1d2a3f
ggml-zdnn: add inputs logging
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:11:09 +08:00
Aaron Teo e695e8577d
ggml-zdnn: add tensor to pre_tfm_desc logging
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-30 13:06:36 +08:00
Aaron Teo 8dbca74fc7
ggml-zdnn: attempt to use unique ptr
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 17:03:58 +08:00
Aaron Teo b1376ad051
ggml-zdnn: add weights logging to check
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 16:38:07 +08:00
Aaron Teo b28b423801
ggml-zdnn: switch to using deque to fix pointer deref problem
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 15:55:33 +08:00
Aaron Teo 3446807452
ggml-zdnn: attempt at fixing invalid buffer
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 15:45:46 +08:00
Aaron Teo 2d45ee2536
ggml-zdnn: add init_tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 15:36:42 +08:00
Aaron Teo ab60ae6ca2
ggml-zdnn: add zdnn_init call for static libs
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:55:44 +08:00
Aaron Teo 0ae2d30302
ggml-zdnn: add nnpa installed detection
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:39:55 +08:00
Aaron Teo a9438925f2
ggml-zdnn: add parmblkformat detections
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:36:55 +08:00
Aaron Teo 1c6ca76c2e
ggml-zdnn: remove free_buffer debug info
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:27:16 +08:00
Aaron Teo 1a0520a540
ggml-zdnn: add logging to debug free buffer
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:12:18 +08:00
Aaron Teo 2872276d8a
ggml-zdnn: fix invalid ztensor buffer release
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-29 00:09:00 +08:00
Aaron Teo 2cfa118fa9
ggml-zdnn: fix missing load tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 23:42:24 +08:00
Aaron Teo fc9260deab
ggml-zdnn: attempt to fix sigsegv
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 23:37:50 +08:00
Aaron Teo e0549c2925
ggml-zdnn: fix missing vector import in header
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 23:33:37 +08:00
Aaron Teo f99b274cac
ggml-zdnn: fix missing vector import
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 23:30:48 +08:00
Aaron Teo 0905168388
ggml-zdnn: rewrite into mre
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 23:26:15 +08:00
Aaron Teo 03ec5d3ed3
ggml-zdnn: bring back working matmul
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 18:14:44 +08:00
Aaron Teo 4cc62cb693
ggml-zdnn: move bias data to local also
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 18:10:14 +08:00
Aaron Teo 6f42570194
ggml-zdnn: move everything back to local declaration
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 18:08:47 +08:00
Aaron Teo eefa943b0a
ggml-zdnn: fix sigsegv
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 18:03:17 +08:00
Aaron Teo fc692ed498
ggml-zdnn: figure out why sigtrap is happening
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 18:00:28 +08:00
Aaron Teo 08de84ef85
ggml-zdnn: bugfix transform ztensor vs origtensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:57:57 +08:00
Aaron Teo 032dce5a6a
ggml-zdnn: fix sequencing of transforms
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:46:17 +08:00
Aaron Teo cf0e190c40
ggml-zdnn: add more safeguards in matmul
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:44:39 +08:00
Aaron Teo f239bbb02d
ggml-zdnn: move weights transform into mulmat
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:38:44 +08:00
Aaron Teo 092fa3a328
ggml-zdnn: activate bias transform in matmul
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:27:35 +08:00
Aaron Teo f7e8d6f2b2
ggml-zdnn: add logger to check if mat mul ops go through set_tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:17:12 +08:00
Aaron Teo 6d71749c26
ggml-zdnn: add more debug info for extra buffer transform
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:10:07 +08:00
Aaron Teo 4b2f1cb1b8
ggml-zdnn: add bias data transform
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 16:05:53 +08:00
Aaron Teo f800c80281
ggml-zdnn: add bias ztensor and data free
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 15:59:52 +08:00
Aaron Teo bee7dd3020
ggml-zdnn: tighten memory usage, change string allocation
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 15:55:42 +08:00
Aaron Teo aef93b3908
ggml-zdnn: add bias init_tensor
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
2025-07-28 15:41:56 +08:00