CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-13 10:57:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,118 Commits 501 Branches 4,779 Tags
12e6b8b65d3bc942f4432776ec1045d296f7fa67
Commit Graph

1190 Commits

Author SHA1 Message Date
Aaron Teo
12e6b8b65d Merge branch 'master' into feat/backend-zdnn 2025-07-31 02:00:01 +08:00
uvos
ad4a700117 HIP: enable mfma mmq on gfx908 and gfx90a for select datatypes and shapes (#14949) 2025-07-30 17:38:06 +02:00
Kai Pastor
e228de9449 cmake : Fix BLAS link interface (ggml/1316) 2025-07-30 17:33:11 +03:00
Kai Pastor
73a8e5ca03 vulkan : fix 32-bit builds (ggml/1313) 
The pipeline member can be cast to VkPipeline.
This is a VkPipeline_T* on 64 bit but a uint64_t on 32 bit.
Cf. VK_DEFINE_NON_DISPATCHABLE_HANDLE documentation.
 2025-07-30 17:33:11 +03:00
Johannes Gäßler
92b8810ec7 CUDA: skip masked KV slices for all FA kernels (#14924) 2025-07-30 15:46:13 +02:00
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
uvos
aa79524c51 HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only AMD targets (#14945) 2025-07-29 20:23:04 +02:00
uvos
b77d11179d HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. (#14930) 
This is useful for testing for regressions on GCN with CDNA hardware.

With GGML_HIP_MMQ_MFMA=Off and GGML_CUDA_FORCE_MMQ=On we can conveniently test the GCN code path on CDNA. As CDNA is just GCN renamed with MFMA added and limited use ACC registers, this provides a good alternative for regression testing when GCN hardware is not available.
 2025-07-29 17:44:30 +02:00
uvos
c7aa1364fd HIP: Ignore unsupported unroll transformation in fattn-vec (#14931) 
llvm with the amdgcn target dose not support unrolling loops with conditional break statements, when those statements can not be resolved at compile time. Similar to other places in GGML lets simply ignore this warning.
 2025-07-29 17:43:43 +02:00
hipudding
204f2cf168 CANN: Add ggml_set_rows (#14943) 2025-07-29 22:36:43 +08:00
Sigbjørn Skjæret
138b288b59 cuda : add softcap fusion (#14907) 2025-07-29 14:22:03 +02:00
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
Aman Gupta
0a5036bee9 CUDA: add roll (#14919) 
* CUDA: add roll

* Make everything const, use __restrict__
 2025-07-29 14:45:18 +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
xctan
db16e2831c ggml-cpu : deduplicate scalar implementations (#14897) 
* remove redundant code in riscv

* remove redundant code in arm

* remove redundant code in loongarch

* remove redundant code in ppc

* remove redundant code in s390

* remove redundant code in wasm

* remove redundant code in x86

* remove fallback headers

* fix x86 ggml_vec_dot_q8_0_q8_0
 2025-07-28 17:40:24 +02:00
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
Akarshan Biswas
cd1fce6d4f SYCL: Add set_rows support for quantized types (#14883) 
* SYCL: Add set_rows support for quantized types

This commit adds support for GGML_OP_SET_ROWS operation for various
quantized tensor types (Q8_0, Q5_1, Q5_0, Q4_1, Q4_0, IQ4_NL) and BF16
type in the SYCL backend.

The quantization/dequantization copy kernels were moved from cpy.cpp
to cpy.hpp to make them available for set_rows.cpp.

This addresses part of the TODOs mentioned in the code.

* Use get_global_linear_id() instead

ggml-ci

* Fix formatting

ggml-ci

* Use const for ne11 and size_t variables in set_rows_sycl_q

ggml-ci

* Increase block size for q kernel to 256

ggml-ci

* Cleanup imports

* Add float.h to cpy.hpp
 2025-07-28 20:32:15 +05:30
Johannes Gäßler
946b1f6859 CUDA: fix pointer incrementation in FA (#14916) 2025-07-28 14:30:22 +02:00
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