Nikita Sarychev
cae9fb4361
HIP: Only call rocblas_initialize on rocblas versions with the multiple instantation bug ( #11080 )
...
This disables the workaround on rocblas fixed versions (>=4.0.0) to eliminate the runtime cost and unnecessary VRAM allocation of loading all tensile objects.
2025-01-28 16:42:20 +01:00
Eric Curtin
7fee2889e6
Add github protocol pulling and http:// ( #11465 )
...
As pulling protocols to llama-run
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-28 14:45:41 +00:00
Nuno
d7d1eccacc
docker: allow installing pip packages system-wide ( #11437 )
...
Signed-off-by: rare-magma <rare-magma@posteo.eu>
2025-01-28 14:17:25 +00:00
someone13574
4bf3119d61
cmake : don't fail on GGML_CPU=OFF ( #11457 )
2025-01-28 15:15:34 +01:00
Nuno
f643120bad
docker: add perplexity and bench commands to full image ( #11438 )
...
Signed-off-by: rare-magma <rare-magma@posteo.eu>
2025-01-28 10:42:32 +00:00
Akarshan Biswas
6e84b0ab8e
SYCL : SOFTMAX F16 mask support and other fixes ( #11261 )
...
Implemented ggml_sycl_op_soft_max() F16 src1(mask) support for which a pragma deprecation warning was added during #5021 .
To do this, had to decouple it from ggml_sycl_op_flatten which always considered src1 to be of fp32 type(many OP functions are dependent on it).
* SYCL: SOFTMAX F16 mask support and other fixes
* test-backend-ops: Add F16 mask test cases
2025-01-28 09:56:58 +00:00
Michael Engel
2b8525d5c8
Handle missing model in CLI parameters for llama-run ( #11399 )
...
The HTTP client in llama-run only prints an error in case the download of
a resource failed. If the model name in the CLI parameter list is missing,
this causes the application to crash.
In order to prevent this, a check for the required model parameter has been
added and errors for resource downloads get propagated to the caller.
Signed-off-by: Michael Engel <mengel@redhat.com>
2025-01-28 08:32:40 +00:00
Eric Curtin
a4417ddda9
Add new hf protocol for ollama ( #11449 )
...
https://huggingface.co/docs/hub/en/ollama
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-27 19:36:10 +01:00
Haus1
d6d24cd9ed
AMD: parse the architecture as supplied by gcnArchName ( #11244 )
...
The value provided by minor doesn't include stepping for AMD, parse the value returned by gcnArchName instead to retrieve an accurate ID.
2025-01-27 14:58:17 +01:00
lexasub
a5203b4465
llama : minor fixes for up llama load model speed ( #11448 )
...
* impl::load change map bpe_ranks to onordered map for reduce time of impl::load on 30%
* llama_model_loader::init_mapping - replace new llama_mmap to std::make_unique<llama_mmap> for clean code & reduce (/2) time of running init_mappings
* Update src/llama-vocab.cpp
---------
Co-authored-by: lexasub <empty@empty.ru>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-01-27 14:42:09 +01:00
Johannes Gäßler
df984e0147
llama: refactor llama_decode_impl ( #11381 )
2025-01-27 12:07:12 +01:00
Ihar Hrachyshka
acd38efee3
metal: Handle null returned from MTLCreateSystemDefaultDevice() ( #11441 )
...
This fixes segmentation fault error when running tests when no metal
devices are available (for example, when not linked with Core Graphics
framework or otherwise).
2025-01-27 09:41:59 +02:00
Xuan Son Nguyen
caf773f249
docker : fix ARM build and Vulkan build ( #11434 )
...
* ci : do not fail-fast for docker
* build arm64/amd64 separatedly
* fix pip
* no fast fail
* vulkan: try jammy
2025-01-26 22:45:32 +01:00
Georgi Gerganov
178a7eb952
metal : use residency sets ( #11427 )
...
* metal : use residency sets
ggml-ci
* metal : restore commandBufferWithUnretainedReferences calls [no ci]
* metal : release descriptors
ggml-ci
* metal : check env GGML_METAL_NO_RESIDENCY
ggml-ci
* metal : fix build + clean-up
ggml-ci
2025-01-26 20:06:16 +02:00
Nuno
6f53d8a6b4
docker: add missing vulkan library to base layer and update to 24.04 ( #11422 )
...
Signed-off-by: rare-magma <rare-magma@posteo.eu>
2025-01-26 18:22:43 +01:00
bandoti
19f65187cb
cmake: add ggml find package ( #11369 )
...
* Add initial ggml cmake package
* Add build numbers to ggml find-package
* Expand variables with GGML_ prefix
* Guard against adding to cache variable twice
* Add git to msys2 workflow
* Handle ggml-cpu-* variants
* Link ggml/ggml-base libraries to their targets
* Replace main-cmake-pkg with simple-cmake-pkg
* Interface features require c_std_90
* Fix typo
* Removed unnecessary bracket from status message
* Update examples/simple-cmake-pkg/README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update examples/simple-cmake-pkg/README.md
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-01-26 12:07:48 -04:00
Frank Mai
1d8ee06000
rpc: fix register position ( #11424 )
...
Signed-off-by: thxCode <thxcode0824@gmail.com>
2025-01-26 16:20:34 +01:00
Georgi Gerganov
2cc9b8c32c
readme : update hot topics
2025-01-26 14:30:15 +02:00
Jeff Bolz
f35726c2fb
build: apply MSVC /bigobj option to c/cpp files only ( #11423 )
2025-01-26 03:10:03 +01:00
Jeff Bolz
4a75d19376
vulkan: compile shaders on-demand ( #11406 )
...
Reduce first-run startup time and memory consumption.
Should fix #11339 .
2025-01-25 22:29:57 +01:00
uvos
26771a1491
Hip: disable VMM on hip as it seams that it dosent work in some configurations ( #11420 )
2025-01-25 21:01:12 +01:00
Jeff Bolz
ca6baf76c1
build: add /bigobj to MSVC build ( #11407 )
2025-01-25 11:26:37 -06:00
Diego Devesa
6e264a905b
docker : add GGML_CPU_ARM_ARCH arg to select ARM architecture to build for ( #11419 )
2025-01-25 17:22:41 +01:00
Xuan Son Nguyen
49b0e3cec4
server : fix cleaning up stream task ( #11418 )
...
* server : fix cleaning up stream task
* one more spot
2025-01-25 16:36:44 +01:00
Diego Devesa
20a758155b
docker : fix CPU ARM build ( #11403 )
...
* docker : fix CPU ARM build
* add CURL to other builds
2025-01-25 15:22:29 +01:00
Georgi Gerganov
00c24acb2a
ci : fix line breaks on windows builds ( #11409 )
...
* ci : fix line breaks on windows builds
* cont : another try
* ci : fix powershell line breaks
2025-01-25 13:36:48 +02:00
jiahao su
466ea66f33
CANN: Add Ascend CANN build ci ( #10217 )
...
* CANN: Add Ascend CANN build ci
* Update build.yml
* Modify cann image version
* Update build.yml
* Change to run on x86 system
* Update build.yml
* Update build.yml
* Modify format error
* Update build.yml
* Add 'Ascend NPU' label restrictions
* Exclude non PR event
Co-authored-by: Yuanhao Ji <jiyuanhao@apache.org>
* Update build.yml
---------
Co-authored-by: Yuanhao Ji <jiyuanhao@apache.org>
2025-01-25 00:26:01 +01:00
uvos
5f0db9522f
hip : Add hipGraph and VMM support to ROCM ( #11362 )
...
* Add hipGraph support
* Enable VMM on rocm
2025-01-25 00:02:23 +01:00
Johannes Gäßler
c5d9effb49
CUDA: fix FP16 cuBLAS GEMM ( #11396 )
2025-01-24 21:02:43 +01:00
uvos
9fbadaef4f
rocBLAS: Avoid fp32->fp16->fp32 conversion on cdna ( #11356 )
2025-01-24 17:50:49 +01:00
Georgi Gerganov
9755129c27
release : pack /lib in the packages ( #11392 )
...
* release : pack /lib and /include in the packages
* cmake : put libs in /bin
* TMP : push artifacts
* Revert "TMP : push artifacts"
This reverts commit 4decf2c4df537b09e70f
2025-01-24 18:41:30 +02:00
Jafar Uruç
a07c2c8a52
docs : Update readme to build targets for local docker build ( #11368 )
2025-01-24 14:30:13 +01:00
Johannes Gäßler
8137b4bb2b
CPU/CUDA: fix (GQA) mul mat back, add CUDA support ( #11380 )
2025-01-24 12:38:31 +01:00
Bernhard M. Wiedemann
1af6945eb0
cmake : avoid -march=native when reproducible build is wanted ( #11366 )
...
See https://reproducible-builds.org/ for why this is good
and https://reproducible-builds.org/specs/source-date-epoch/
for the definition of this variable.
Without this patch, compiling on different machines produced different binaries, which made verification of results difficult.
Fixes : #11317
This patch was done while working on reproducible builds for openSUSE.
2025-01-24 13:21:35 +02:00
Eric Curtin
01f37edf1a
Update llama-run README.md ( #11386 )
...
For consistency
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-24 09:39:24 +00:00
stduhpf
c07e87f38b
server : (webui) put DeepSeek R1 CoT in a collapsible <details> element ( #11364 )
...
* webui : put DeepSeek R1 CoT in a collapsible <details> element
* webui: refactor split
* webui: don't use regex to split cot and response
* webui: format+qol
* webui: no loading icon if the model isn't generating
* ui fix, add configs
* add jsdoc types
* only filter </think> for assistant msg
* build
* update build
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2025-01-24 09:02:38 +01:00
Jeff Bolz
564804b79b
tests: fix some mul_mat test gaps ( #11375 )
...
Now that we have batched mat-vec mul Vulkan shaders for up to n==8,
these tests weren't actually exercising the mat-mat mul path. Test
n==9 as well. Also, change to use all_types.
2025-01-23 14:51:24 -06:00
Eric Curtin
05f63cc9ee
Update documentation ( #11373 )
...
To show -n, -ngl, --ngl is acceptable.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-23 20:04:31 +00:00
Eric Curtin
f7fb43cd0b
Add -ngl ( #11372 )
...
Most other llama.cpp cli tools accept -ngl with a single dash.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-23 16:16:18 +00:00
Xuan Son Nguyen
5845661640
server : add more clean up when cancel_tasks is called ( #11340 )
...
* server : add more clean up when cancel_tasks is called
* fix recv_with_timeout
* std::remove_if
* fix std::remove_if
2025-01-23 13:56:05 +01:00
Eric Curtin
f211d1dc10
Treat hf.co/ prefix the same as hf:// ( #11350 )
...
ollama uses hf.co/ to specify huggingface prefix, like RamaLama
uses hf://
Treat them similarly.
Signed-off-by: Eric Curtin <ecurtin@redhat.com>
2025-01-23 10:38:20 +00:00
amd-dwang
955a6c2d91
Vulkan-run-test: fix mmq_wg_denoms ( #11343 )
...
There should be a copy-and-paste error here.
*mmq_wg_denoms should be used together with *warptile_mmq, instead of
wg_denoms.
2025-01-23 08:14:28 +01:00
Jeff Bolz
1971adf55e
vulkan: sort shaders for more deterministic binary ( #11315 )
...
Fixes #11306 .
2025-01-23 08:07:50 +01:00
Jeff Bolz
5245729e33
vulkan: fix diag_mask_inf ( #11323 )
...
With robustbufferaccess disabled, this shader was showing OOB stores. There
is a bounds check in the code, but the workgrouop dimensions were reversed vs
CUDA and it was running the wrong number of threads. So fix the workgroup
dimensions and disable robustness for this pipeline.
2025-01-23 08:01:17 +01:00
Diego Devesa
6152129d05
main : update README documentation for batch size ( #11353 )
...
* main : update README documentation for batch size
* fix formatting
* minor
2025-01-22 19:22:20 +01:00
Georgi Gerganov
16d3df7ab0
readme : add plugin links ( #11355 )
2025-01-22 19:44:26 +02:00
Diego Devesa
12c2bdf2de
server : fix draft context not being released ( #11354 )
2025-01-22 17:44:40 +01:00
Olivier Chafik
c64d2becb1
minja: sync at 0f5f7f2b37 ( #11352 )
2025-01-22 16:16:27 +00:00
Jiří Podivín
96f4053934
Adding logprobs to /v1/completions ( #11344 )
...
Signed-off-by: Jiri Podivin <jpodivin@redhat.com>
2025-01-22 12:51:32 +01:00
Olivier Chafik
a94f3b2727
common: utils to split / join / repeat strings (from json converter) (#11342 )
...
* Factor string_join, string_split, string_repeat into common
* json: refactor to surface a versatile builder
* Update common.cpp
2025-01-22 09:51:44 +00:00
