lhez
73e53dc834
opencl: ref count ggml_backend_opencl_context and refactor profiling ( #14254 )
...
* Move profiling info into `ggml_backend_opencl_context`
* Add `enqueue_ndrange_kernel` to launch kernel
2025-06-24 11:46:25 -07:00
Georgi Gerganov
62af464227
batch : fix check for empty sequences in memory ( #14364 )
...
* batch : fix check for empty sequences in memory
ggml-ci
* cont : reuse the var
ggml-ci
2025-06-24 18:26:30 +03:00
Mathieu Baudier
c148cf1946
cmake : use LLAMA_BUILD_NUMBER when defining LLAMA_INSTALL_VERSION ( #14362 )
2025-06-24 15:05:31 +02:00
Nigel Bosch
1b809cee22
server : move no API key doc to /health ( #14352 )
2025-06-24 10:59:11 +02:00
Sigbjørn Skjæret
abf241045d
main : honor --verbose-prompt on interactive prompts ( #14350 )
2025-06-24 09:31:00 +02:00
Bartowski
901e20bbe5
jinja : Add Mistral-Small-3.2-24B-Instruct-2506.jinja ( #14349 )
...
This will allow the use of tools on the llama-server
2025-06-24 09:17:58 +03:00
uvos
0142961a2e
CUDA/HIP: optimize mmv paths taken for HIP devices ( #14324 )
...
Co-authored-by: Johannes Gäßler <johannesg@5d6.de >
2025-06-24 01:12:56 +02:00
bandoti
ce82bd0117
ci: add workflow for relocatable cmake package ( #14346 )
2025-06-23 15:30:51 -03:00
Jeff Bolz
bf2a99e3cb
vulkan: update windows SDK in release.yml ( #14344 )
2025-06-23 15:44:48 +02:00
Molly Sophia
72c6bc3f3d
llama : better rwkv chat template and add missing inputs.use_jinja setting ( #14336 )
...
* llama-cli : add missing `inputs.use_jinja` setting
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* llama : better legacy chat template for rwkv
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
---------
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
2025-06-23 19:56:19 +08:00
Johannes Gäßler
defe2158dd
CUDA: mul_mat_v support for batch sizes > 1 ( #14262 )
...
* CUDA: mul_mat_v support for batch sizes > 1
* use 64 bit math for initial offset calculation
2025-06-23 13:11:31 +02:00
Georgi Gerganov
7b50d589a8
kv-cells : fix tracking of seq_pos ( #14339 )
...
* kv-cells : fix tracking of seq_pos during cache reuse
ggml-ci
* cont : improve error message
ggml-ci
* cont : add more comments
2025-06-23 12:27:35 +03:00
Jeff Bolz
3a9457df96
vulkan: update windows SDK in CI ( #14334 )
2025-06-23 10:19:24 +02:00
Ed Addario
fa4a9f2a1c
quantize : handle user-defined pruning of whole layers (blocks) ( #13037 )
2025-06-22 23:16:26 +02:00
Sigbjørn Skjæret
238005c2dc
gguf-py : fix SpecialVocab parsing when post_processor is null ( #14330 )
2025-06-22 19:46:17 +02:00
Ruikai Peng
66aba7aca9
run : avoid double tokenization ( #14327 )
...
* run : avoid double tokenization by adopting common_tokenize heuristic
* build : fix windows gcc and clang warnings
* lint : fixed trailing whitepace
* run : fix is_first flag
2025-06-23 01:28:06 +08:00
Georgi Gerganov
f1f5e82df6
examples : fix is_first logic for tokenization ( #14329 )
...
ggml-ci
2025-06-22 20:10:07 +03:00
uvos
af3373f1ad
HIP: enable vec fattn on RDNA4 ( #14323 )
2025-06-22 16:51:23 +02:00
yuiseki
5d5c066de8
mtmd : fix Pixtral OOM with large images by capping image_size to 1024 ( #14326 )
...
Mistral Small 2506 models using Pixtral vision encoder were running out
of GPU memory when processing images larger than 1024x1024 pixels due to
exponential memory growth from unlimited image size.
This fix applies the same 1024x1024 limit used by Qwen2VL models to
prevent OOM issues while maintaining compatibility with existing models.
2025-06-22 14:44:57 +02:00
Sigbjørn Skjæret
40bfa04c95
common : use std::string_view now that we target c++17 ( #14319 )
2025-06-22 08:37:43 +03:00
Aman Gupta
aa064b2eb7
CUDA: add mean operation ( #14313 )
...
* CUDA: add mean operation
* add back sum_rows_f32_cuda
* Review: early exit if col!=0
2025-06-22 12:39:54 +08:00
Sigbjørn Skjæret
aa0ef5c578
gguf-py : fix Qwen3-Embedding eos token ( #14314 )
2025-06-21 18:12:05 +02:00
Markus Tavenrath
bb16041cae
Add support for VK_EXT_debug_utils to add labels to Vulkan objects. ( #13792 )
...
* Add support for VK_EXT_debug_utils to add labels to Vulkan objects. In step 1 compute pipelines are getting labeled.
* remove #ifdef for debug utils and add queue marker.
2025-06-21 08:17:12 +02:00
Sigbjørn Skjæret
58cba76a9a
gguf-py : fix TemplateProcessing pair when bos/eos is missing ( #14312 )
2025-06-21 07:33:21 +02:00
Georgi Gerganov
67ae5312e2
metal : fix thread-safety ( #14300 )
...
ggml-ci
2025-06-21 08:04:18 +03:00
Georgi Gerganov
692e3cdd0a
memory : rename interface to llama_memory_context_i ( #14296 )
...
* memory : rename interface to llama_memory_context_i
ggml-ci
* cont : fix comments
* cont : use "mctx" for referencing a memory context
ggml-ci
2025-06-21 08:03:46 +03:00
Daniel Han
b23fa0b3f4
convert : fix Llama 4 conversion ( #14311 )
2025-06-21 06:32:01 +02:00
Georgi Gerganov
06cbedfca1
sync : ggml
...
ggml-ci
2025-06-20 21:02:47 +03:00
Acly
b7147673f2
Add ggml_roll (ggml/1274)
...
* ggml : add ggml_roll
* use set/get_op_params & std::min
2025-06-20 21:02:47 +03:00
David Chiu
d860dd99a4
docs : fix the link to llama.h ( #14293 )
2025-06-20 19:43:35 +02:00
Aman Gupta
c959f462a0
CUDA: add conv_2d_transpose ( #14287 )
...
* CUDA: add conv_2d_transpose
* remove direct include of cuda_fp16
* Review: add brackets for readability, remove ggml_set_param and add asserts
2025-06-20 22:48:24 +08:00
Sigbjørn Skjæret
22015b2092
lint : remove trailing whitepace ( #14304 )
2025-06-20 16:37:44 +02:00
Ruikai Peng
dd6e6d0b6a
vocab : prevent tokenizer overflow ( #14301 )
...
* vocab : prevent stack overflow in tokenize
* vocab : return error instead of aborting on oversized token count
* vocab : INT32_MIN from llama_tokenize on overflow
2025-06-20 07:13:06 -07:00
Nicolò Scipione
8308f98c7f
sycl: add usage of enqueue_functions extension ( #14244 )
...
* Add header and namespace to use enqueue_functions extension
* Convert submit and parallel_for to use new extension in convert.cpp
* Convert submit and parallel_for to use extension in ggml-sycl.cpp
* Convert submit and parallel_for to use extension in gla.cpp
* Convert submit and parallel_for in mmq.cpp
* Convert submit and parallel_for in mmvq.cpp
* Convert submit and parallel_for in remaining files
* Convert all simple parallel_for to nd_launch from enqueue_functions
extension
* Wrapping extension in general function
Create a general function that enable the enqueue_functions extension if
it is enable in the compiler, otherwise call the general SYCL function
to launch kernels.
---------
Signed-off-by: nscipione <nicolo.scipione@codeplay.com >
2025-06-20 15:07:21 +02:00
Christian Kastner
6369be0735
Implement GGML_CPU_ALL_VARIANTS for PowerPC ( #14286 )
...
* Add PowerPC feature detection and scoring
* ggml-cpu: Implement GGML_CPU_ALL_VARIANTS for PowerPC
* ggml-cpu: Delay some initializations until function is called
When using GGML_BACKEND_DL=ON, these initializations might use
instructions that are not supported by the current CPU.
---------
Co-authored-by: Diego Devesa <slarengh@gmail.com >
2025-06-20 14:17:32 +02:00
Sigbjørn Skjæret
88fc854b4b
llama : improve sep token handling ( #14272 )
2025-06-20 14:04:09 +02:00
Diego Devesa
e28c1b93fd
cuda : synchronize graph capture and cublas handle destruction ( #14288 )
...
Workarounds an issue that may cause CUDA graph capture to fail when a cuBLAS handle is destroyed in a different thread
2025-06-20 13:57:36 +02:00
Georgi Gerganov
d27b3ca175
ggml : fix repack work size for mul_mat_id ( #14292 )
...
ggml-ci
2025-06-20 11:19:15 +03:00
Charles Xu
9230dbe2c7
ggml: Update KleidiAI to v1.9.0 ( #14277 )
2025-06-20 10:51:01 +03:00
Georgi Gerganov
812939a9e9
model : more uniform output id handling ( #14275 )
...
* model : more uniform output id handling
ggml-ci
* cont : revert n_outputs < n_tokens optimization
ggml-ci
* cont : fix out_ids initialization
ggml-ci
2025-06-20 10:50:27 +03:00
Georgi Gerganov
4c9fdfbe15
ubatch : new splitting logic ( #14217 )
...
ggml-ci
2025-06-20 10:14:14 +03:00
Aman Gupta
9eaa51e7f0
CUDA: add conv_2d_dw ( #14265 )
...
* CUDA: add conv_2d_dw
* better naming
* simplify using template
* Review: fix operation ordering in ggml-cuda, use __forceinline__, use more const
2025-06-20 09:50:24 +08:00
Diego Devesa
8f71d0f3e8
ggml-cpu : remove unnecesary arm feature detection ( #14281 )
...
Support for Arm runtime feature detection has now been added to GGML_CPU_ALL_VARIANTS. This removes the old and not very functional code.
2025-06-19 21:24:14 +02:00
Alex Trotta
381174bbda
gguf-py : make sentencepiece optional ( #14200 )
...
* Make sentencepiece optional
* Bump to 0.18.0
* Bump patch instead of minor
Co-authored-by: compilade <git@compilade.net >
---------
Co-authored-by: compilade <git@compilade.net >
2025-06-19 15:56:12 +02:00
aa956
d67341dc18
server : add server parameters for draft model cache type ( #13782 )
...
Co-authored-by: aa956 <27946957+aa956@users.noreply.github.com >
2025-06-19 16:01:03 +03:00
fanyang
456af35eb7
build : suppress gcc15 compile warnings ( #14261 )
...
* Change _contains_any() substrs to std::string_view and fix the find comparison logic.
2025-06-19 14:49:48 +02:00
Anton Mitkov
600e3e9b50
sycl: Cleanup codepaths in Get Rows in sycl backend ( #14215 )
...
Addresses unused reorder path
2025-06-19 11:40:21 +01:00
bashayer hijji
fffcce535e
llama-bench : add --no-warmup flag ( #14224 ) ( #14270 )
...
Add no_warmup parameter to cmd_params struct and command-line parsing to allow users to skip warmup runs before benchmarking.
- Add no_warmup boolean field to cmd_params struct
- Add --no-warmup command-line argument parsing
- Add help text documentation for the new flag
- Wrap existing warmup logic in conditional check
- Maintain full backward compatibility (warmup enabled by default)
Addresses #14224
2025-06-19 12:24:12 +02:00
pqnet
5fc7856815
convert : fix remote option in Windows ( #14100 )
2025-06-19 12:21:40 +02:00
Aaron Teo
faed5a5f5d
llamafile : support s390x SIMD instruction set ( #14273 )
2025-06-19 11:48:54 +02:00
