Commit Graph

508 Commits

Author SHA1 Message Date
02f0430141 Disable GL_KHR_cooperative_matrix Vulkan extension if not available. (#11117)
* Disable GL_KHR_cooperative_matrix Vulkan extension if not available.

* Perform Vulkan extensions checks in a more sensible order

* Remove unnecessary #ifdef directive
2025-01-08 09:18:13 +01:00
bec2183f2c fix: Vulkan shader gen binary path when Cross-compiling (#11096)
* fix: Vulkan shader gen binary path when cross compiling
2025-01-08 09:17:29 +01:00
53ff6b9b9f GGUF: C++ refactor, backend support, misc fixes (#11030)
* GGUF: C++ refactor, backend support, misc fixes

remove ggml_tensor.backend

update CODEOWNERS [no ci]

remove gguf_get_data from API

revise GGUF API data types
2025-01-07 18:01:58 +01:00
017cc5f446 ggml-backend : only offload from host buffers (fix) (#11124) 2025-01-07 16:11:57 +01:00
a3d50bc022 ggml-backend : only offload from host buffers (#11120) 2025-01-07 12:38:05 +01:00
a4dd490069 rpc : code cleanup (#11107)
Remove duplicated macros, use GGML_LOG_ERROR for errors
2025-01-07 08:37:02 +02:00
c0d6f790d0 SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6 (#11087)
* SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6

* Revert "SYCL: Use get_multi_ptr instead of deprecated get_pointer in wkv6"

This reverts commit f62dc45f31.

* Reland: Use get_multi_ptr instead of deprecated get_pointer in wkv6
2025-01-07 14:26:07 +08:00
46e3556e01 CUDA: add BF16 support (#11093)
* CUDA: add BF16 support
2025-01-06 02:33:52 +01:00
b56f079e28 Vulkan: Add device-specific blacklist for coopmat for the AMD proprietary driver (#11074)
* Vulkan: Add device-specific blacklist for coopmat for the AMD proprietary driver

* Add (TM) to AMD name check
2025-01-04 21:09:59 +01:00
f922a9c542 [GGML][RPC] Support for models with non-512-aligned tensors over RPC. (#11047)
* Added init tensor calling code

* Added get_alloc_size forwarding

* Cleaned up and improved type/error handling.

* fix: remove trailing whitespaces.

* Cleanup and use GGML error logging functions.

* Handle potentially dangerous edge cases.

* Apply suggestions from code review

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2025-01-04 17:10:30 +01:00
5e3b08d606 ggml : do not install metal source when embed library (ggml/1054) 2025-01-04 16:09:53 +02:00
db68c93b57 ggml : improve inputs log sched_print_assignments (ggml/1053)
This commit attempts to improve the log message for the inputs of the
splits in the sched_print_assignments function.

The motivation for this change is that currently even if there are no
inputs a colon is displayed at the end of the line, which can make it a
little confusing when reading the output as it could be interpreted as
the line below are inputs when they are in fact nodes. With this change
the colon will only be printed if there actually are inputs.
2025-01-04 16:09:53 +02:00
c31fc8b966 fix: Vulkan shader gen binary path (#11037) 2025-01-04 09:17:31 +01:00
e7da954ecc metal : avoid uint (#11019) 2025-01-03 11:26:14 +02:00
0827b2c1da ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027)
* Fixes for clang AVX VNNI

* enable AVX VNNI and alder lake build for MSVC

* Apply suggestions from code review

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-12-31 15:23:33 +01:00
6e1531aca5 common, examples, ggml : fix MSYS2 GCC compiler errors and warnings when building with LLAMA_CURL=ON and GGML_OPENCL=ON (#11013)
In common/common.cpp:
* Convert usage of stat() function call to check if file exists to standard library function std::filesystem::exists (error unable to match to correct function signature)
* Additional conditions to check if PATH_MAX is already defined in WIN32 environment (warning it is already defined in MSYS2)

In examples/run/run.cpp:
* Add io.h header inclusion (error cannot find function _get_osfhandle)
* Change initialisers for OVERLAPPED to empty struct (warning about uninitialised members)
* Add initialiser for hFile (warning it may be uninitialised)
* Add cast for curl_off_t percentage value to long int in generate_progress_prefix function (warning that curl_off_t is long long int)

In ggml/src/ggml-opencl/ggml-opencl.cpp:
* Initialise certain declared cl_mem variables to nullptr for greater safety (warning about B_d variable possibly used unassigned)
2024-12-31 01:46:06 +01:00
716bd6dec3 vulkan: optimize mul_mat for small values of N (#10991)
Make the mul_mat_vec shaders support N>1 (as a spec constant, NUM_COLS) where
the batch_strides are overloaded to hold the row strides. Put the loads from the
B matrix in the innermost loop because it should cache better.

Share some code for reducing the result values to memory in mul_mat_vec_base.
2024-12-30 18:27:11 +01:00
a813badbbd vulkan: im2col and matmul optimizations for stable diffusion (#10942)
* tests: Add im2col perf tests

* vulkan: optimize im2col, more elements per thread

* vulkan: increase small tile size for NV_coopmat2

* vulkan: change im2col to 512 elements per workgroup
2024-12-29 10:16:34 +01:00
fdd2188912 vulkan: Use push constant offset to handle misaligned descriptors (#10987) 2024-12-29 09:35:11 +01:00
Eve
d79d8f39b4 vulkan: multi-row k quants (#10846)
* multi row k quant shaders!

* better row selection

* more row choices

* readjust row selection

* rm_kq=2 by default
2024-12-26 16:54:44 +01:00
d283d02bf2 examples, ggml : fix GCC compiler warnings (#10983)
Warning types fixed (observed under MSYS2 GCC 14.2.0):
* format '%ld' expects argument of type 'long int', but argument has type 'size_t'
* llama.cpp/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp:81:46: warning: missing initializer for member '_STARTUPINFOA::lpDesktop' [-Wmissing-field-initializers]  (emitted for all struct field except first)
2024-12-26 14:59:11 +01:00
2cd43f4900 ggml : more perfo with llamafile tinyblas on x86_64 (#10714)
* more perfo with llamafile tinyblas on x86_64.

- add bf16 suport
- change dispache strategie (thanks:
https://github.com/ikawrakow/ik_llama.cpp/pull/71 )
- reduce memory bandwidth

simple tinyblas dispache and more cache freindly

* tinyblas dynamic dispaching

* sgemm: add M blocs.

* - git 2.47 use short id of len 9.
- show-progress is not part of GNU Wget2

* remove not stable test
2024-12-24 18:54:49 +01:00
60cfa728e2 ggml : use wstring for backend search paths (#10960)
ggml-ci
2024-12-24 04:05:27 +01:00
3327bb0f8d ggml : fix arm enabled features check (#10961) 2024-12-24 04:05:17 +01:00
32d6ee6385 ggml : fix const usage in SSE path (#10962) 2024-12-23 20:25:52 +01:00
7024d59e6a ggml : fix run-time on FreeBSD in get_executable_path() (#10948) 2024-12-23 01:20:11 +01:00
ebdee9478c vulkan: build fixes for 32b (#10927)
* vulkan: build fixes for 32b

Should fix #10923

* vulkan: initialize some buffer/offset variables
2024-12-22 10:44:01 +01:00
a91a41364b vulkan: optimize coopmat2 dequant functions (#10855)
Change the code to do 16b loads when possible and extract the appropriate
component late, so the code is effectively decoding a pair of elements and
then selecting one. This can allow more commoning to happen in the compiler
when neighboring elements are loaded.
2024-12-21 08:04:45 +01:00
e34c5af43f ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0() (#10874)
* ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0()

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* ggml-cpu: format code

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2024-12-21 00:33:37 +01:00
eb5c3dc64b SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)
* Migrate to tensor->buffer for checking backend buffer type: 1

* SYCL: common.cpp try to migrate away from tensor->backend

* SYCL: fix assertions and add proper comments

* SYCL: remove extra space

* SYCL: Add back static to ggml_backend_buffer_is_sycl_split function

* SYCL: Add pragma directive to suppress warning spam

* SYCL: Integrate debug logs with GGML_LOG and other fixes

* Revert "SYCL: Integrate debug logs with GGML_LOG and other fixes"

This reverts commit 2607b7de0f.
Let's keep the current SYCL specific logging mechanism for now

* SYCL: Use GGML_SYCL_DEBUG after reverting

* SYCL: reg_get_proc_address func, update to the current func signature

* SYCL: Refactor SYCL buffer checks in ggml_sycl_cpy_tensor_2d
2024-12-20 23:31:28 +08:00
21ae3b9be8 ggml : add test for SVE and disable when it fails (#10906) 2024-12-20 13:31:28 +01:00
a3c33b1dce ggml: fix arm build with gcc (#10895)
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
2024-12-19 14:20:41 +01:00
9177484f58 ggml : fix arm build (#10890)
* ggml: GGML_NATIVE uses -mcpu=native on ARM

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* ggml: Show detected features with GGML_NATIVE

Signed-off-by: Adrien Gallouët <angt@huggingface.co>

* remove msvc support, add GGML_CPU_ARM_ARCH option

* disable llamafile in android example

* march -> mcpu, skip adding feature macros

ggml-ci

---------

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
Co-authored-by: Adrien Gallouët <angt@huggingface.co>
2024-12-18 23:21:42 +01:00
0bf2d10c55 tts : add OuteTTS support (#10784)
* server : add "tokens" output

ggml-ci

* server : output embeddings for all tokens when pooling = none

ggml-ci

* server : be explicit about the pooling type in the tests

ggml-ci

* server : do not normalize embeddings when there is no pooling

ggml-ci

* llama : add OuteTTS support (wip)

* wip

* extract features

* first conv

* group norm

* resnet conv

* resnet

* attn

* pos net

* layer norm

* convnext

* head

* hann window

* fix n_embd + remove llama.cpp hacks

* compute hann window

* fft

* spectrum processing

* clean-up

* tts : receive input text and generate codes

* clip : fix new conv name

* tts : minor fix

* tts : add header + minor fixes

ggml-ci

* tts : add matchematical constant

ggml-ci

* tts : fix sampling + cut initial noise

* tts : fixes

* tts : update default samplers

ggml-ci

* tts : text pre-processing

* tts : outetts-voc -> wavtokenizer-dec

* tts : remove hardcoded constants

ggml-ci

* tts : fix tensor shapes

* llama : refactor wavtokenizer tensors

ggml-ci

* cont

ggml-ci

* cont [no ci]

* llama : update WavTokenizer to non-causal attn

* llama : handle no-vocab detokenization

* tts : add Python example for OuteTTS (wip)

* tts : extend python example to generate spectrogram

ggml-ci

* server : fix rebase artifacts

* tts : enable "return_tokens" in Python example

ggml-ci

* tts : minor fixes

* common : support HF download for vocoder
2024-12-18 19:27:21 +02:00
081b29bd2a tests: add tests for GGUF (#10830) 2024-12-17 19:09:35 +01:00
78f766768d cmake : fix "amd64" processor string (whisper/2638) 2024-12-17 18:35:49 +02:00
8dd19a4812 vulkan : fix soft_max.comp division by zero (whisper/2633)
This change prevents a division by zero error when p.KY is 0.
2024-12-17 18:35:49 +02:00
130d0c90bd ggml : remove return from ggml_gallocr_allocate_node (ggml/1048)
This commit removes the return statement from ggml_gallocr_allocate_node
function.

The motivation behind this change is to make the code more readable and
consistent.
2024-12-17 18:35:49 +02:00
3919da8e33 ggml : add check for grad_accs (ggml/1046)
* ggml : add check for grad_accs

This commit adds a check for grad_accs in ggml_graph_get_grad and
ggml_graph_get_grad_acc functions. This is necessary to avoid segfaults
when grad_accs is not initialized.

The motivation for this change is that I find it nice to be able to
print out a computation graph using ggml_graph_print but this function
segfaults when grad_accs is not initialized:
```console
(gdb) p g1
$2 = (ggml_cgraph *) 0x7ffff66004b0
(gdb) p *g1
$3 = {size = 2048, n_nodes = 1, n_leafs = 2, nodes = 0x7ffff6600500,
grads = 0x0, grad_accs = 0x0, leafs = 0x7ffff6604500,
visited_hash_set = {size = 4099, used = 0x7ffff6610518,
keys = 0x7ffff6608500}, order = GGML_CGRAPH_EVAL_ORDER_LEFT_TO_RIGHT}
(gdb) p ggml_graph_print(g1)
=== GRAPH ===
n_nodes = 1

Program received signal SIGSEGV, Segmentation fault.
0x0000555555579775 in ggml_graph_get_grad
(cgraph=0x7ffff66004b0,node=0x7ffff6600340)
    at /ggml/ggml/src/ggml.c:5990
5990  return igrad != GGML_HASHSET_FULL &&
          ggml_bitset_get(cgraph->visited_hash_set.used, igrad) ?
          cgraph->grads[igrad] : NULL;
```

* squash! ggml : add check for grad_accs

Fix the check in ggml_graph_get_grad. The check was incorrectly using
cgraph->grad_accs instead of cgraph->grads.
2024-12-17 18:35:48 +02:00
0006f5a74a ggml : update ggml_backend_cpu_device_supports_op (#10867)
* ggml : fix cpy op for IQ-quants to use reference impl

ggml-ci

* ggml : disable tests involving i-matrix quantization

* ggml : update ggml_backend_cpu_device_supports_op

ggml-ci
2024-12-17 18:35:42 +02:00
Eve
7b1ec53f56 vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10809)
* ensure mul mat shaders work on systems with subgroup size less than 32

more fixes

add test

* only s_warptile_mmq needs to be run with 32 threads or more
2024-12-17 06:52:55 +01:00
160bc039c8 rwkv6: add wkv6 support for Vulkan backend (#10829)
* rwkv_wkv6 vulkan shader

* RWKV_WKV6 Vulkan op tests passed

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* Apply code format changes

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>

* add [[unroll]] and remove unnecessary conditions

* add uma support

* fix erros in EditorConfig Checker

---------

Signed-off-by: Molly Sophia <mollysophia379@gmail.com>
Co-authored-by: Molly Sophia <mollysophia379@gmail.com>
2024-12-16 22:00:46 +01:00
ba1cb19cdd llama : add Qwen2VL support + multimodal RoPE (#10361)
* Barebone Qwen2VL LLM convertor

* Add Qwen2VL cli entrypoint

* [WIP] add qwen2vl arch

* Verify m-rope output

* Add vl-rope/2d-rope support for qwen2vl ViT

* update qwen2vl cli tool

* update 5D tensor op workaround

* [WIP] qwen2vl vision model

* make batch and clip utils compatible with qwen2vl

* [WIP] create inference workflow, gguf convert script but fix

* correcting vision-rope behavior, add the missing last layer back to ViT

* add arg parser to qwen2vl_surgery

* replace variable size array with vector

* cuda-gdb cmake preset

* add fp32 mrope, vision rope kernel

* add fp16 support for qwen2vl and m-rope

* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`

* fix rope op mode switching, out dated func args

* update `llama_hparams`

* update to keep up stream changes

* resolve linter, test errors

* add makefile entry, update speical image padding token

* add mrope unit test, fix few compiler warnings

* rename `mrope` related function, params

* minor updates on debug util, bug fixs

* add `m-rope` testcase to `test-backend-ops`

* Apply suggestions from code review

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

* fix traililng whitespce

* store `llama_hparams.rope_sections` with fixed size array

* update position id tensor size check in GGML_OP_ROPE

* minor updates

* update `ggml_backend_*_supports_op` of unsupported backends

* remote old `rope_section` compare operator

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-12-14 14:43:46 +02:00
a76c56fa1a Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
* [cl][adreno] Add Adreno GPU support

Add new OpenCL backend to support Adreno GPUs

---------

Co-authored-by: Skyler Szot <quic_sszot@quicinc.com>
Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
Co-authored-by: Alexander Angus <quic_aangus@quicinc.com>
Co-authored-by: Hongqiang Wang <quic_wangh@quicinc.com>
Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>

* [cl][ci] Add workflow for CL

* [cl][adreno] Fix memory leak for non SMALL_ALLOC path

* opencl: integrate backend dyn.load interface and fix compiler and format warnings

* opencl: remove small-alloc support and fix build errors for non-opencl platforms

* opencl: fixed merge conflict (MUSA added twice in cmake)

* opencl-ci: use RUNNER_TEMP instead of github.workspace

* opencl: fix embed tool invocation with python3

* opencl: CI workflow fixes

* opencl: Clean up small-alloc in CMake files

* opencl: cleanup ggml-opencl2 header file

* opencl: use ulong for offsets and strides in ADD kernel

* opencl: use cl_ulong for all offsets

* opencl: use cl_ulong for sizes and strides

* opencl: use `GGML_LOG_xxx` instead of `fprintf(stderr, ...)`

* opencl: rename backend `opencl2` -> `opencl`

* opencl: rename kernel files `ggml-opencl2` -> `ggml-opencl`

* opencl: make OpenCL required, remove redundant lib and inc directories

* `ggml-base`, `..` and `.` are added by `ggml_add_backend_library`

* opencl: rename backend - funcs, structs, etc `opencl2` -> `opencl`

* opencl: remove copyright marker since main license already covers

* opencl: replace some more OPENCL2 leftovers

* opencl: remove limits on `tensor_extra`

* opencl: use pools for `tensor_extra`

* opencl: fix compiler warnings with GCC and Clang

Still getting the warning about clCreateCmdQueue being obsolete.
Will fix that separately.

* opencl: fail gracefully if opencl devices are not available

Also for unsupported GPUs.

* opencl: fix MSVC builds (string length error)

* opencl: check for various requirements, allow deprecated API

* opencl: update log message for unsupported GPUs

---------

Co-authored-by: Skyler Szot <quic_sszot@quicinc.com>
Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
Co-authored-by: Alexander Angus <quic_aangus@quicinc.com>
Co-authored-by: Hongqiang Wang <quic_wangh@quicinc.com>
Co-authored-by: Max Krasnyansky <quic_maxk@quicinc.com>
2024-12-13 12:23:52 -08:00
9f35e44592 Fix crash caused by ggml_backend_load_all when launching on Android Activity (#10812)
* Fix crash caused by ggml_backend_load_all when launching on AndroidActivity.

Details:
Calling ggml_backend_load_all during initialization in the AndroidActivity project leads to a crash with the error:
terminating with uncaught exception of type std::__ndk1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied [./].
This issue occurs because AndroidActivity restricts file access due to sandboxing.

Reproduction:
In the example folder, the LlamaAndroid project can reproduce the crash by calling ggml_backend_load_all first in Java_android_llama_cpp_LLamaAndroid_backend_1init.

* Update ggml/src/ggml-backend-reg.cpp

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-13 13:56:07 +01:00
Eve
64ae065511 vulkan: small mul_mat_vec optimizations (#10665)
* double the number of rows per workgroup

* Update ggml-vulkan.cpp

* Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats

* only increase the number of rows for amd and subgroup size 64

* fix missing NUM_ROWS for mul_mat_vec_iq4_nl_f16_f32, untested

* use subgroup min and max to check for gcn (requires https://github.com/ggerganov/llama.cpp/pull/10721)

* manual merge ggml-vulkan.cpp

* set min and max subgroup size in any case

* Also double the number of rows for Intel GPUs
2024-12-13 09:42:04 +01:00
83ed24a97b SYCL: Reduce most of the compiler warnings (#10748)
* Try to reduce some unused and typecast warnings

* Reduce compiler warnings step 2

* add a newline at the end of the file

* Initialize nreduce as size_t

* [SYCL] Remove pragma directives from mmq.cpp

* SYCL: mmq add condition to prevent blocks_per_tile_x_row variable from becoming 0

* SYCL softmax: Initialize nreduce as size_t

* ggml-sycl.cpp: fix some trailing whitespaces

* SYCL: remove the unused variables instead of commenting it out

* SYCL poo2d kernel: set NAN for invalid pooling op

* SYCL gemm.hpp: remove pragma directives

* SYCL gemm.hpp: use const cast to properly support dnnl::memory

* SYCL: wkv6 remove a comment

* SYCL: clean comments step 2

* SYCL: clean comments and variables step 3

* SYCL: Use GGML_UNUSED for unused variables

* SYCL: remove extra empty lines and a comment

* Remove TODO

* cleanup spaces

* add a stdout for unsupported op

* use sycl printf over fprintf

* remove prints for CI

* SYCL ggml-sycl: pool2D use sycl::nan and remove if-else block

---------

Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-12-13 12:12:15 +05:30
d583cd03f6 ggml : Fix compilation issues on ARM platform when building without fp16 (#10811) 2024-12-13 01:04:19 +01:00
8faa1d4dd4 CUDA: faster non-contiguous concat (#10760)
* faster uncontiguous concat

* Use a lambda to avoid code duplication

Co-authored-by: Diego Devesa <slarengh@gmail.com>

* Update ggml/src/ggml-cuda/concat.cu

* add constexpr  and static assert

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
2024-12-12 19:09:50 +01:00
cb13ef85a4 remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
other windows build fixes
2024-12-12 19:02:49 +01:00