vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 18:30:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
9181 commits 3 branches 237 tags 1.2 GiB
Commit graph

9181 commits

This branch
This branch
All branches
Author SHA1 Message Date
Concedo
35707f4e97 split vulkan into two compilation units for faster build 2025-08-20 12:12:47 +08:00
Concedo
56c0926866 fix metal build 2025-08-19 15:41:16 +08:00
Concedo
a6bbd449c4 Merge commit '19f4decae0' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	tests/test-backend-ops.cpp
 2025-08-19 15:00:32 +08:00
Concedo
140ae92886 Merge commit '65349f26f2' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
 2025-08-19 11:35:32 +08:00
Concedo
9fb0611115 handle contractions correctly, bump defaults 2025-08-18 22:33:44 +08:00
Concedo
2abe11071b custom voice handling 2025-08-18 16:57:34 +08:00
Concedo
67ef5e6c02 phonemizer fixes, now kokoro works very well 2025-08-18 16:13:16 +08:00
Concedo
3f621be7dd wip, adding IPA for kokoro 2025-08-18 00:51:12 +08:00
Concedo
3138a151c2 improve hparams for tts 2025-08-17 22:07:13 +08:00
Dong Won Kim
19f4decae0
vulkan: support sqrt (#15370) 2025-08-17 16:03:09 +02:00
Concedo
685129fb5a add missing title, set max tts length to 1024, updated lite (+2 squashed commit) 
Squashed commit:

[0737a028] add missing title

[a42328b0] add max tts length 1024
 2025-08-17 21:42:56 +08:00
Sigbjørn Skjæret
4d196981d4
convert : force patch_embd weights to F16 or F32 to avoid broken GGUFs (#15367) 
* force patch_embd weights to f32

* use MmprojModel base tensor_force_quant instead
 2025-08-17 14:47:42 +02:00
Sigbjørn Skjæret
b143fbc87a
ci : fix hang in windows-hip build/release (#15365) 
* fix hang in windows-latest-cmake-hip

* apply fix to release as well
 2025-08-17 13:30:23 +02:00
Concedo
bcaf379509 tts.cpp merged and working in kcpp! 2025-08-17 18:09:28 +08:00
Jeff Bolz
de5627910d
vulkan: Optimize argsort (#15354) 
- Launch an appropriate number of invocations (next larger power of two).
32 invocations is common and the barrier is much cheaper there.
- Specialize for "needs bounds checking" vs not.
- Make the code less branchy and [[unroll]] the loops. In the final code,
I see no branches inside the main loop (only predicated stores) when
needs_bounds_check is false.
- Always sort ascending, then apply the ascending vs descending option when
doing the final stores to memory.
- Copy the values into shared memory, makes them slightly cheaper to access.
 2025-08-17 10:41:45 +02:00
Concedo
52606e9b1d tts cpp model is now loadable in kcpp 2025-08-17 15:47:22 +08:00
Concedo
9935ac093f standardize tts linting and formatting 2025-08-17 14:11:30 +08:00
Concedo
cfc1a0d4ef tts cpp cli builds and runs fine. 2025-08-17 13:53:27 +08:00
Tarek Dakhran
65349f26f2
model : support vision LiquidAI LFM2-VL family (#15347) 
* wip lfm2 vision model

* Fix conv weight

* Implement dynamic resolution

* Fix cuda

* support LFM2-VL-450M

* happy CI

* Remove extra `ggml_conv` and put others into the right place

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
 2025-08-16 23:33:54 +02:00
Jeff Bolz
1fe00296f5
vulkan: fuse adds (#15252) 
* vulkan: fuse adds

Fuse adds that have the same shape, which are common in MoE models.
It will currently fuse up to 6 adds, because we assume no more than
8 descriptors per dispatch. But this could be changed.

* check runtimeDescriptorArray feature

* disable multi_add for Intel due to likely driver bug
 2025-08-16 11:48:22 -05:00
Concedo
bc04366a65 builds but crashes 2025-08-17 00:09:03 +08:00
Jeff Bolz
de2192794f
vulkan: Support mul_mat_id with f32 accumulators (#15337) 
* vulkan: Add missing bounds checking to scalar/coopmat1 mul_mat_id

* vulkan: Support mul_mat_id with f32 accumulators, but they are not hooked up

- There's no explicit way to request f32 precision for mul_mat_id, but there
probably should be, and this gets the code in place for that.
- A couple fixes to check_results.
- Remove casts to fp16 in coopmat1 FA shader (found by inspection).
 2025-08-16 11:18:31 +02:00
Jeff Bolz
2e2b22ba66
vulkan: Add missing bounds checking to scalar/coopmat1 mul_mat_id (#15334) 2025-08-16 10:58:38 +02:00
Concedo
2bf128587d modify ggml core to support tts 2025-08-16 16:52:34 +08:00
rmatif
912ff8c119
OpenCL: add initial FA support (#14987) 
* add F16/F16 fa support

* fix kernel init

* use mad instead of fma

* use inline function

* mark FA with sinks as unsupported for now

* add pragma unroll to loops
 2025-08-16 01:05:55 -07:00
Concedo
d876898476 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/cpu.Dockerfile
#	.devops/cuda.Dockerfile
#	.github/ISSUE_TEMPLATE/010-bug-compilation.yml
#	.github/ISSUE_TEMPLATE/011-bug-results.yml
#	.github/labeler.yml
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CODEOWNERS
#	README.md
#	docs/build-s390x.md
#	docs/ops.md
#	examples/eval-callback/eval-callback.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/transpose.cl
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-opt.cpp
 2025-08-16 12:39:25 +08:00
Concedo
9491b6966d updated lite (+1 squashed commits) 
Squashed commits:

[36a56d8c] updated lite
 2025-08-16 12:26:27 +08:00
Daniel Bevenius
5e6229a840
common : fix double bos, use common_chat_templates for add_bos and add_eos (#15326) 
This commit updates common_chat_templates_apply_jinja to use the
the add_bos and add_eos parameters from the chat template instead of
the inputs.

The motivation for this is that currently if the `add_bos` and `add_eos`
from the input parameters are used it is possible to there will be a
missmatch between the model and the chat template which can lead to the
the removal of duplicate BOS/EOS tokens in chat.cpp `apply` to not
happen leading to two BOS tokens being added to the template.
 2025-08-15 19:50:52 +02:00
lhez
e2c1bfff53
opencl: add initial mxfp4 support via mv (#15270) 
* opencl: add reference `mul_mv_mxfp4_f32`

* opencl: add reference `mul_mv_id` for mxfp4

* Q4_0 tranpose fix for Adreno

---------

Co-authored-by: shawngu-quic <shawngu@qti.qualcomm.com>
 2025-08-15 09:52:14 -07:00
Georgi Gerganov
5edf1592fd
vulkan : fix out-of-bounds access in argmax kernel (#15342) 
ggml-ci
 2025-08-15 16:16:36 +02:00
Georgi Gerganov
db3010bd23
vulkan : fix compile warnings on macos (#15340) 
ggml-ci
 2025-08-15 15:28:28 +02:00
Aaron Teo
ff27f80a74
ggml: initial IBM zDNN backend (#14975) 
* ggml-zdnn: inital backend impl

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: temp change z17 to arch15

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: fix build bugs

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: tensor->extra logging check

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add layout name mapping, ztensor information

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: separate logging into its own line

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add shape comparison

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: add ggml_tensor shape log

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

ggml-zdnn: fix incorrect shape logging

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add output buffer check

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: run compute and store into tensor->extra

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add set_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add more loggers

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: update set_tensor logging to check only for matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: last working matmul version

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add comments to prevent accidentally deleting lines

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: support op out_prod

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: update op out_prod to use tensor->extra

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: rewrite the backend implementation

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: bugfix new impl

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix compiler warnings and bugfixes

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: test ztensor finding in init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: implement at least 1 op to test

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: assign tensor->extra to buffer

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add check for view tensors to prevent init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: rework init_tensor to create new buffers

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: switch to std vector instead of array

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: switch buffers back and set to arbitrary number

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: impl init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: update supports_op matmul matrix

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix incorrect ztensor shape, reduce memory padding

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: code clean up

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: impl matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix compiler error missing type

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix missing data transform call

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add bias init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: tighten memory usage, change string allocation

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add bias ztensor and data free

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add bias data transform

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add more debug info for extra buffer transform

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add logger to check if mat mul ops go through set_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: activate bias transform in matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: move weights transform into mulmat

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add more safeguards in matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix sequencing of transforms

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: bugfix transform ztensor vs origtensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: figure out why sigtrap is happening

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix sigsegv

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: move everything back to local declaration

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: move bias data to local also

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: bring back working matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: rewrite into mre

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix missing vector import

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix missing vector import in header

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt to fix sigsegv

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix missing load tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix invalid ztensor buffer release

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add logging to debug free buffer

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: remove free_buffer debug info

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add parmblkformat detections

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add nnpa installed detection

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add zdnn_init call for static libs

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt at fixing invalid buffer

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: switch to using deque to fix pointer deref problem

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add weights logging to check

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt to use unique ptr

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add tensor to pre_tfm_desc logging

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add inputs logging

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: disable op_none initialisation for testing

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix missing return from init_tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: load ztensors in cgraph exec

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: work on moving output ztensor as well

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: disable logging and breakpoints for full test

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt at manually changing the layout

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt at using default nwhc format instead

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: disable global load ztensor for now

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix errorenous output load tensor

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: add guards to prevent loading ztensor if transformed

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: code cleanup

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: bring load ztensor back to init routine

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: code clean up

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix ztensor deallocation abort

stabilise ggml <-> zdnn api

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: clean up matmul selection

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: clean up project structure

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: update documentation, prepare for upstream

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* chore: add codeowners

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: disable batched matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: attempt at fixing tensor views during matmul

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: deny all view tensors directly

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix pr comments

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* docs: update ops docs for zdnn

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: redo test-backend-ops for ops.md

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix typo in build-s390x.md

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* codeowners: remove taronaeo for now

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* Revert "codeowners: remove taronaeo for now"

This reverts commit 411ea4ed78d08778967bd0bd33a6538cfcbe082f.

* ggml-zdnn: remove unused ggml_zdnn macro

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

---------

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2025-08-15 21:11:22 +08:00
Sigbjørn Skjæret
d3248d9b65
ci : fix ios-xcode-build (#15324) 
* fix ios-xcode-build

* use xcode-select with fixed version

* switch to macos-15 to get xcode 16.4
 2025-08-15 14:02:39 +02:00
Diego Devesa
7aeee88cfe
ci : move ccache action to ggml-org fork (#15328) 2025-08-15 12:27:02 +02:00
Johannes Gäßler
b07791aa1d
test-opt: fix backend support check (#15317) 
* test-opt: fix backend support check

* Update tests/test-opt.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2025-08-15 11:23:17 +02:00
Johannes Gäßler
4227c9be42
CUDA: fix negative KV_max values in FA (#15321) 2025-08-14 23:21:24 +02:00
Georgi Gerganov
df36bce667
eval-callback : stop on first NaN (#15320) 
* eval-callback : stop on first NaN

* cont : log error
 2025-08-14 22:10:51 +03:00
Diego Devesa
f75b830647
chat : include kwargs in template example (#15309) 2025-08-14 10:28:29 -07:00
Concedo
c6f76034d7 updated android termux script (+1 squashed commits) 
Squashed commits:

[1977086c] updated android termux script (+1 squashed commits)

Squashed commits:

[b7f2b92f] updated android termux script
 2025-08-15 00:16:33 +08:00
Daniel Bevenius
7a0de96045
llama : add 18-layer model type for Gemma 3-270m (#15319) 
This commit adds support for the 18-layer model type in the Gemma3
series, which is the size of the Gemma3-270m model.

The motivation for this commit is was the only change required for
Gemma3-270m to be converted to GGUF format and used with llama.cpp.

Once the model has been converted and uploaded to Huggingface it can be
used like this:
```console
$ ./build/bin/llama-cli -hf ggml-org/gemma-3-270m-GGUF:Q8_0
```
 2025-08-14 17:56:26 +02:00
simevo
e4e915912c
devops : fix compile bug when the BASE_CUDA_DEV_CONTAINER is based on Ubuntu 24.04 (#15005) 
fixes #15004

Co-authored-by: Paolo Greppi <paolo.greppi@libpf.com>
 2025-08-14 18:45:27 +03:00
Concedo
5a921a40f9 add overridenativecontext flag, stop nagging me 2025-08-14 22:54:45 +08:00
uvos
5ba36f6103
HIP: Cleanup hipification header (#15285) 
add expicit conversion operator to support older versions of rocm
Switch over to hip_bf16 from legacy hip_bfloat16
Simplify RDNA3 define
Reduce swap over of new hipblas api to rocm 6.5 as this version is used for rocm 7.0 previews

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
 2025-08-14 16:23:56 +02:00
Aldehir Rojas
b204a5a234
gpt-oss: implement harmony parsing (#15181) 
* model : add harmony parser for gpt-oss

* gpt-oss : fix grammar trigger from causing empty stack

* gpt-oss: tweak the grammar trigger again

* gpt-oss : add support for recipient in role header

* gpt-oss : fix ungrouped tool calls in grammar

* gpt-oss : loosen function name matching during parse

* gpt-oss : clean up workarounds

* gpt-oss : add template tests

* gpt-oss : simulate thinking and tool call tags

* gpt-oss : undo think tags when reasoning_format is none

* gpt-oss : set special tokens back to user defined

* gpt-oss : update openai-gpt-oss template

* server : filter out harmony thought messages

* gpt-oss : simplify parsing
 2025-08-14 17:23:11 +03:00
Christian Kastner
646944cfa8
docker : Enable GGML_CPU_ALL_VARIANTS for ARM (#15267) 2025-08-14 16:22:58 +02:00
Georgi Gerganov
1a01899b61
readme : update hot topics (#15315) 2025-08-14 17:16:03 +03:00
Concedo
7ac0102ed3 hope i didnt break anything 2025-08-14 21:42:24 +08:00
Jeff Bolz
863d341eeb
vulkan: perf_logger improvements (#15246) 
* vulkan: perf_logger improvements

- Account for batch dimension in flops calculation.
- Fix how "_VEC" is detected for mat_mul_id.
- Fix "n" dimension for mat_mul_id (in case of broadcasting).
- Include a->type in name.

* use <=mul_mat_vec_max_cols rather than ==1
 2025-08-14 08:38:10 -05:00
Concedo
d5876024ec Merge commit 'f4586ee598' into concedo_experimental 
# Conflicts:
#	README.md
#	docs/multimodal/minicpmo2.6.md
#	docs/multimodal/minicpmv2.6.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/add.cl
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tools/perplexity/perplexity.cpp
#	tools/server/README.md
 2025-08-14 21:29:52 +08:00
Georgi Gerganov
d32e03f449
server : add SWA checkpoints (#15293) 
* server : add SWA checkpoints

ggml-ci

* cont : server clean-up

* server : handle state restore fails

* llama : add extended llama_state_seq_ API

* server : do not make checkpoints if --swa-full

ggml-ci

* llama : remove flags value for NONE

* server : configure number of SWA checkpoints with CLI arg

ggml-ci

* args : fix scope of new argument
 2025-08-14 14:59:50 +03:00