vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 17:44:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3
8610 commits 3 branches 196 tags 389 MiB
Commit graph

188 commits

Author SHA1 Message Date
Concedo
d383c03554 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	tests/test-backend-ops.cpp
 2025-06-29 15:10:26 +08:00
Jeff Bolz
63a7bb3c7e
vulkan: handle noncontig in the final case of ggml_vk_get_cpy_pipeline (#14378) 2025-06-28 17:36:40 +02:00
Jeff Bolz
00d5282c7f
vulkan: lock accesses of pinned_memory vector (#14333) 2025-06-28 17:17:09 +02:00
Concedo
b884a7f058 try switch back to size max for vulkan 2025-06-24 23:14:24 +08:00
Concedo
fb13e3e51b Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	src/llama-context.cpp
#	tests/test-backend-ops.cpp
 2025-06-22 23:26:15 +08:00
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
0cc4m
10bb545c5b
Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer (#14249) 2025-06-19 09:15:42 +02:00
Concedo
9e49350507 merge occam's https://github.com/ggml-org/llama.cpp/pull/14249 2025-06-18 21:23:23 +08:00
Concedo
4356a00f4a Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	ci/run.sh
#	docs/function-calling.md
#	examples/gritlm/gritlm.cpp
#	ggml/CMakeLists.txt
#	ggml/cmake/common.cmake
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	requirements/requirements-compare-llama-bench.txt
#	scripts/compare-llama-bench.py
#	tests/CMakeLists.txt
 2025-06-18 00:16:54 +08:00
Jeff Bolz
c89c2d1ab9
vulkan: mutex around vkQueueSubmit (#14127) 
This fixes the remaining crash in test-thread-safety on my system.
 2025-06-16 08:21:08 +02:00
Concedo
69e4a32ca2 Merge commit 'd4e0d95cf5' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	common/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
 2025-06-14 01:58:53 +08:00
Jeff Bolz
bd248d4dc7
vulkan: Better thread-safety for command pools/buffers (#14116) 
This change moves the command pool/buffer tracking into a vk_command_pool
structure. There are two instances per context (for compute+transfer) and
two instances per device for operations that don't go through a context.
This should prevent separate contexts from stomping on each other.
 2025-06-11 09:48:52 -05:00
Jeff Bolz
1f7d50b293
vulkan: Track descriptor pools/sets per-context (#14109) 
Use the same descriptor set layout for all pipelines (MAX_PARAMETER_COUNT == 8)
and move it to the vk_device. Move all the descriptor pool and set tracking to
the context - none of it is specific to pipelines anymore. It has a single vector
of pools and vector of sets, and a single counter to track requests and a single
counter to track use.
 2025-06-11 07:19:25 +02:00
0cc4m
97340b4c99
Vulkan: Don't default to CPU device (like llvmpipe), even if no other device is available, to allow fallback to CPU backend (#14099) 2025-06-10 13:01:33 +01:00
Concedo
d33c88b1f4 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	ci/run.sh
#	examples/embedding/embedding.cpp
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	src/CMakeLists.txt
 2025-06-06 17:56:51 +08:00
Masato Nakasaka
669c13e0f6
vulkan: Enable VK_KHR_cooperative_matrix extension for Intel Xe2 GPUs (#14001) 
* allowing B580 and U9-288V

* experimenting code to detect Xe2

* allowing coopmat only for Xe2 GPUs

* fixed comment wording

* fixed comment wording

* removed unnecessary driver check
 2025-06-05 16:00:29 +02:00
Jeff Bolz
5a8ae3053c
vulkan: automatically deduce size of push constants (#13936) 2025-06-05 07:17:58 +02:00
Concedo
bc89b465a8 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	README.md
#	docs/build.md
#	docs/install.md
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
 2025-06-05 11:03:34 +08:00
Ervin Áron Tasnádi
0d3984424f
ggml-vulkan: adds support for op CONV_TRANSPOSE_1D (#13813) 
* * ggml-vulkan: adds op CONV_TRANSPOSE_1D

* test-backend-ops: adds more spohisticated tests for CONV_TRANSPOSE_1D

* Missing barrier added to shader.
Number of additional tests reduced to 108.

* * Fixes typo in variable name.

* Removes extra whitespaces.

* Adds int64->int32 casts to prevent possible warnings.

* Problem size reduced in tests to pass tests with llvmpipe.

* supports_op condition moved from unintended position
 2025-06-04 22:02:00 +02:00
Jeff Bolz
7e00e60ef8
vulkan: fix warnings in perf logger querypool code (#13937) 2025-06-03 20:30:22 +02:00
Concedo
b42b618897 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	README.md
#	examples/parallel/parallel.cpp
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/gguf.cpp
#	scripts/sync-ggml.last
#	tests/test-gguf.cpp
 2025-06-02 23:26:43 +08:00
Kai Pastor
108009f5c7 vulkan : Remove unexpected ; (ggml/1253) 2025-06-01 13:43:57 +03:00
Concedo
c987abf9f5 Merge commit '763d06edb7' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-linux-cross.yml
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/mtmd/mtmd.cpp
#	tools/server/CMakeLists.txt
 2025-05-31 12:44:18 +08:00
Jeff Bolz
bef8176387
vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817) 
Also change it to be controlled by an env var rather than cmake flag
 2025-05-27 18:39:07 +02:00
Concedo
8c701d7ded Merge commit '72b090da2c' into concedo_experimental 
# Conflicts:
#	docs/backend/CANN.md
#	docs/function-calling.md
#	examples/embedding/embedding.cpp
#	examples/retrieval/retrieval.cpp
#	ggml/src/ggml-cann/CMakeLists.txt
#	ggml/src/ggml-cann/Doxyfile
#	ggml/src/ggml-cann/acl_tensor.cpp
#	ggml/src/ggml-cann/acl_tensor.h
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/concat.cpp
#	ggml/src/ggml-sycl/conv.cpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/getrows.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/gla.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/outprod.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-sycl/tsembd.cpp
#	ggml/src/ggml-sycl/wkv.cpp
#	scripts/compare-commits.sh
#	tests/test-chat.cpp
#	tests/test-sampling.cpp
 2025-05-28 00:28:41 +08:00
Jeff Bolz
fef693dc6b
vulkan: mark IM2COL as supporting non-contig (#13783) 2025-05-26 06:02:07 +02:00
Concedo
55cc9acec5 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/release.yml
#	README.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
 2025-05-24 12:10:36 +08:00
Jeff Bolz
1dcd01960c
vulkan: support CPY from any type to itself (#13695) 
Reuse the f16/f32 copy shaders, and just scale the number of elements
according to the type size.
 2025-05-23 06:45:02 +02:00
Jeff Bolz
c10ed6cbcc
vulkan: Disable coopmat/coopmat2/bfloat extensions if glslc doesn't support it (#13696) 2025-05-23 06:33:45 +02:00
Judd
a127ff1780
use LOG_WARN to replace std::cerr (#13657) 2025-05-23 06:33:08 +02:00
Concedo
da7fd4aa57 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/musa.Dockerfile
#	.github/workflows/build.yml
#	README.md
#	ci/README.md
#	docs/docker.md
#	examples/lookahead/lookahead.cpp
#	examples/lookup/lookup.cpp
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-musa/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/test-arg-parser.cpp
 2025-05-21 23:12:22 +08:00
Concedo
3fefb3bdf2 Merge commit 'f0adb80bf7' into concedo_experimental 
# Conflicts:
#	docs/backend/CANN.md
#	docs/backend/SYCL.md
#	docs/docker.md
#	examples/sycl/run-llama2.sh
#	examples/sycl/win-run-llama2.bat
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tools/llama-bench/README.md
 2025-05-21 19:10:57 +08:00
Eve
fb1cab201c
vulkan: fix warnings (#13626) 
* small fixes

* remove ifdef
 2025-05-20 21:35:16 +00:00
0cc4m
8960efd0a6
Vulkan: Add f32 accumulator support to quantized mul mat to fix GLM4 32B incoherence (#13607) 2025-05-19 17:54:08 +02:00
Concedo
59300dbdf5 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/actions/windows-setup-curl/action.yml
#	.github/workflows/build-linux-cross.yml
#	README.md
#	common/CMakeLists.txt
#	examples/parallel/README.md
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	tools/server/README.md
 2025-05-18 23:27:53 +08:00
Jeff Bolz
4f41ee11d6
vulkan: use scalar FA rather than coopmat2 when N==1 (#13554) 2025-05-17 08:35:47 +02:00
Concedo
e5d26a2356 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	common/CMakeLists.txt
#	docs/backend/SYCL.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-sycl/CMakeLists.txt
#	ggml/src/ggml-sycl/binbcast.cpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/dequantize.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	ggml/src/gguf.cpp
#	scripts/compare-llama-bench.py
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
 2025-05-16 15:30:31 +08:00
Jeff Bolz
24e86cae72
vulkan: KHR_coopmat flash attention (#13506) 
This shader uses coopmat1 to do the Q*K^T multiply. The P*V multiply is more
difficult for various reasons so I haven't done it. Performance for this
shader is around 2.5x better than for the scalar shader when doing prompt
processing. Some of the benefit may be from other optimizations like staging
through shared memory, or splitting by rows.
 2025-05-14 11:55:26 +02:00
Jeff Bolz
dc1d2adfc0
vulkan: scalar flash attention implementation (#13324) 
* vulkan: scalar flash attention implementation

* vulkan: always use fp32 for scalar flash attention

* vulkan: use vector loads in scalar flash attention shader

* vulkan: remove PV matrix, helps with register usage

* vulkan: reduce register usage in scalar FA, but perf may be slightly worse

* vulkan: load each Q value once. optimize O reduction. more tuning

* vulkan: support q4_0/q8_0 KV in scalar FA

* CI: increase timeout to accommodate newly-supported tests

* vulkan: for scalar FA, select between 1 and 8 rows

* vulkan: avoid using Float16 capability in scalar FA
 2025-05-10 08:07:07 +02:00
Concedo
0874cd231a Merge remote-tracking branch 'jeffbolz/scalar_fa_3' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
 2025-05-09 17:19:33 +08:00
Concedo
42f6930e13 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-rpc/ggml-rpc.cpp
 2025-05-09 17:18:14 +08:00
Jeff Bolz
02115dcd9a
vulkan: Allow up to 4096 elements for mul_mat_id row_ids (#13326) 
This assert fired running Qwen_Qwen3-30B-A3B-Q2_K.gguf:

GGML_ASSERT(nei0 * nei1 <= 3072);

The tensor is 8 x 512. Increase this array size to accommodate.
 2025-05-09 09:23:41 +02:00
Jeff Bolz
615958f42c vulkan: for scalar FA, select between 1 and 8 rows 2025-05-08 14:34:59 -05:00
Jeff Bolz
e66094276b vulkan: support q4_0/q8_0 KV in scalar FA 2025-05-07 23:53:38 -05:00
Jeff Bolz
989bfb18fc vulkan: load each Q value once. optimize O reduction. more tuning 2025-05-07 15:57:38 -05:00
Jeff Bolz
c747227a57 vulkan: reduce register usage in scalar FA, but perf may be slightly worse 2025-05-07 15:02:11 -05:00
Jeff Bolz
876e6617a7 vulkan: use vector loads in scalar flash attention shader 2025-05-07 13:35:13 -05:00
Jeff Bolz
3a8d954e0c vulkan: always use fp32 for scalar flash attention 2025-05-06 23:08:39 -05:00
Concedo
1377a93a73 Merge commit '5215b91e93' into concedo_experimental 
# Conflicts:
#	.github/workflows/build.yml
#	cmake/x64-windows-llvm.cmake
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/CMakeLists.txt
#	tools/imatrix/imatrix.cpp
#	tools/llava/clip.cpp
#	tools/rpc/rpc-server.cpp
 2025-05-06 23:15:04 +08:00
Jeff Bolz
005756a2a9 vulkan: scalar flash attention implementation 2025-05-05 19:40:45 -05:00