374101fd74
cmake : enable building llama.cpp using system libggml ( #12321 )
...
* cmake: Factor out compiler flag function from ggml
llama.cpps's build requires it, too, and we may want to make use of it
without add_subdirectory(ggml).
* cmake: Enable building against system ggml
This facilitates package maintenance for Linux distributions, where the
libggml library most likely will be shipped as an individual package
upon which a llama.cpp package depends.
2025-03-17 11:05:23 +02:00
b3c9a65673
SYCL: set extras only on GGML_TYPE_Q4_0 ( #12366 )
...
* SYCL: set extras only on GGML_TYPE_Q4_0
* release tensor_extras in reset buffer interface
2025-03-17 09:45:12 +08:00
8ba95dca20
llama : fix OLMo-2-0325-32B-Instruct K-norm size ( #12400 )
2025-03-16 19:46:36 +02:00
dc079cfdff
context : fix init of n_outputs ( #12397 )
...
ggml-ci
2025-03-16 19:29:36 +02:00
7b61bcc87c
ci : add --symlinks to xcframework zip command ( #12409 )
...
This commit adds the --symlinks option to the zip command used to create
the xcframework zip file. This is necessary to create symlinks in the
zip file. Without this option, the Versions symlink is stored as a
regular directory entry in the zip file, rather than as a symlink in the
zip which causes the followig error in xcode:
```console
Couldn't resolve framework symlink for '/Users/danbev/work/ai/llama.cpp/tmp_1/build-apple/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/Current': readlink(/Users/danbev/work/ai/llama.cpp/tmp_1/build-apple/llama.xcframework/macos-arm64_x86_64/llama.framework/Versions/Current): Invalid argument (22)
```
Refs: https://github.com/ggml-org/llama.cpp/pull/11996#issuecomment-2727026377
2025-03-16 18:22:05 +01:00
131107dc91
lite fix admin button display issue when preload story
2025-03-17 00:17:31 +08:00
6888f5495d
allow quantkv with contextshift
2025-03-16 21:48:42 +08:00
e466ce65e2
updated sd metadata
2025-03-16 20:12:43 +08:00
8708403ee9
revert clean
2025-03-16 17:53:35 +08:00
5ef1722d5f
fix for sd
2025-03-16 17:02:42 +08:00
0954e9e476
improve model estimation
2025-03-16 16:14:13 +08:00
5d7c5e9e33
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# examples/tts/tts.cpp
2025-03-16 15:42:39 +08:00
2401502cbd
improvement to tool calling, allowing specific tools to be used
2025-03-16 15:20:08 +08:00
9f7fd63160
revert unwanted change to tool calling
2025-03-16 01:35:48 +08:00
f4c3dd5daa
llama-tts : add '-o' option ( #12398 )
...
* added -o option to specify an output file name
* llama-tts returns ENOENT in case of file write error
note : PR #12042 is closed as superseded with this one.
2025-03-15 17:23:11 +01:00
98eade358a
more rocm include dir
2025-03-15 23:29:00 +08:00
3d35d87b41
SYCL: Delete redundant plus sign and space ( #12391 )
2025-03-15 15:49:03 +01:00
b19bd064c0
SYCL : support non-contiguous tensors in binary ops (add, sub, etc) ( #12399 )
...
* sycl : support non-contiguous tensors in binary ops
* sycl : silence unused variable warning
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com >
2025-03-15 22:19:30 +08:00
67851e5415
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# examples/run/run.cpp
# ggml/src/ggml-cann/aclnn_ops.cpp
2025-03-15 19:54:19 +08:00
e84596ec1a
add config for default gen tokens and bos toggle
2025-03-15 19:53:06 +08:00
bfc30066c9
fixed a clip processing bug
2025-03-15 17:49:49 +08:00
7272165e0e
verbosity
2025-03-15 12:13:04 +08:00
4212f0b8e8
wip on multiple fixes
2025-03-15 10:50:36 +08:00
92a391327e
[CANN]MUL_MAT optimization ( #12382 )
2025-03-15 09:31:08 +08:00
9f2250ba72
Add CLI arg to llama-run to adjust the number of threads used ( #12370 )
...
We default to 4, sometimes we want to manually adjust this
Signed-off-by: Eric Curtin <ecurtin@redhat.com >
2025-03-14 16:41:20 +00:00
774973b8f3
main : add -sysf / --system-prompt-file ( #12249 ) ( #12250 )
...
* add system_prompt_file
* add -sysf / --system-prompt-file
* remove system_prompt_file
2025-03-14 16:57:05 +01:00
4a29e216e7
edit readme
2025-03-14 21:06:55 +08:00
8fcb563613
Load all MoE experts during warmup ( #11571 )
...
* llama : introduce llama_set_warmup() API call that controls warmup mode; use all MoE experts during warmup
* common : use new API to enable warmup mode during model warmup
---------
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com >
2025-03-14 13:47:05 +01:00
d7498e7e8a
added model switching to gguf in admin mode (auto guess layers)
2025-03-14 19:45:55 +08:00
30cb77a900
rename replace_instruct_placeholders field
2025-03-14 18:37:12 +08:00
be3bba67ff
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# src/llama-model.cpp
2025-03-14 18:25:21 +08:00
add2a3aa5a
server: fix "--grammar-file" parameter ( #12285 )
2025-03-14 11:21:17 +01:00
782e1e193a
replaced winclinfo.exe with a simplified simpleclinfo.exe that only provides device names and nothing else (+1 squashed commits)
...
Squashed commits:
[4a73c8d3] replaced winclinfo.exe with a simplified simpleclinfo.exe that only provides device names and nothing else
2025-03-14 18:18:32 +08:00
6a1dd57435
gemma3 template, updated lite, fixed tool calling, reenable ctx shift for gemma3
2025-03-14 17:47:01 +08:00
c522ce4143
graph : simplify attn input build for unified KV cache ( #12381 )
...
ggml-ci
2025-03-14 10:47:44 +02:00
081bee8c64
hparams : add SWA rope parameters ( #12374 )
...
ggml-ci
2025-03-14 09:03:24 +02:00
7dc72db9de
Merge branch 'upstream' into concedo_experimental
2025-03-14 11:58:53 +08:00
0db4ae6237
traded my ink for a pen
2025-03-14 11:58:15 +08:00
84d5475541
llama : fix Gemma3 SWA KV cache shift ( #12373 )
...
* llama : fix Gemma3 SWA KV cache shift
ggml-ci
* hparams : add comment [no ci]
2025-03-13 19:08:07 +02:00
52cf1ded0c
remove unwanted print
2025-03-14 00:24:28 +08:00
bdf2977372
fixed windows ci
2025-03-13 20:45:16 +08:00
0460d92cc3
disable context shifting for gemma3
2025-03-13 20:28:26 +08:00
ca698f0cbe
tweaked sd img metadata
2025-03-13 20:04:29 +08:00
5413be2c1b
sd: add generation parameters to image metadata ( #1416 )
...
Straight adaptation from stable-diffusion.cpp main.cpp.
2025-03-13 19:35:06 +08:00
be7c303410
arg : no n_predict = -2 for examples except for main and infill ( #12364 )
2025-03-13 12:34:54 +01:00
2c9ade61fe
test automatic vk shader rebuilding
2025-03-13 19:34:15 +08:00
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context ( #12181 )
...
* llama : refactor llama_context, llama_kv_cache, llm_build_context
ggml-ci
* graph : don't mutate the KV cache during defrag
ggml-ci
* context : reduce virtuals + remove test function
ggml-ci
* context : move interface implementation to source file + factory
ggml-ci
* graph : move KV cache build functions to llama_context impl
ggml-ci
* graph : remove model reference from build_pooling
ggml-ci
* graph : remove llama_model reference
ggml-ci
* kv_cache : provide rope factors
ggml-ci
* graph : rework inputs to use only unique_ptr, remove attn input abstraction
ggml-ci
* context : remove llama_context_i abstraction
ggml-ci
* context : clean-up
ggml-ci
* graph : clean-up
ggml-ci
* llama : remove redundant keywords (struct, enum)
ggml-ci
* model : adapt gemma3
ggml-ci
* graph : restore same attention ops as on master
ggml-ci
* llama : remove TODO + fix indent
ggml-ci
2025-03-13 12:35:44 +02:00
2048b5913d
server : fix crash when using verbose output with input tokens that are not in printable range ( #12178 ) ( #12338 )
...
* Fix DOS index bug
* Remove new APIs
* remove extra line
* Remove from API
* Add extra newline
* Update examples/server/server.cpp
---------
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com >
2025-03-13 11:10:05 +01:00
e75539e8cb
too many issues without BOS (+1 squashed commits)
...
Squashed commits:
[7138d941] only print bos alert in debug
2025-03-13 16:48:29 +08:00
1ef41c2124
streamline output console log (+1 squashed commits)
...
Squashed commits:
[ca474bdd] streamline output console log
2025-03-13 15:33:49 +08:00
Christian Kastner
Akarshan Biswas
Sigbjørn Skjæret
Georgi Gerganov
Daniel Bevenius
Concedo
marcoStocchi
aubreyli
fairydreaming
Chenguang Li
Eric Curtin
Victor
Wagner Bruna
Xuan-Son Nguyen
Ishaan Gandhi