vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-10-21 13:51:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
16423 commits 3 branches 258 tags 1,017 MiB
Commit graph

385 commits

Author SHA1 Message Date
Concedo
deac43f7d1 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ci/run.sh
#	docs/backend/snapdragon/developer.md
#	docs/ops.md
#	docs/ops/CUDA.csv
#	ggml/src/ggml-backend.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/dma-copy.h
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/hvx-copy.h
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemm_xmem_f16_f32_os8.cl
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/fattn-common.hpp
#	ggml/src/ggml-sycl/fattn-mkl.cpp
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	ggml/src/ggml-sycl/fattn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/memtrace.cpp
#	ggml/src/ggml-sycl/memtrace.hpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/check-release-apiabi.sh
#	tests/fusion/MTL.csv
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tests/test-recurrent-state-rollback.cpp
#	tools/mtmd/clip.cpp
#	tools/server/README.md
 2026-10-09 00:13:54 +08:00
Aman Gupta
a46709b683
RPC: add -sm tensor (#26610) 
* rpc: allow -sm tensor

* fix flush for apple rdma

* move graph_uids to rpc_dispatcher

* cont : fix conflict

* cont: stop spinning dispatcher thread

* remove meta backend change

* add TODO to simplify logic

* rpc: bump major version

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-10-06 20:55:39 +05:30
Aman Gupta
6753a033f0
ggml: refactor selective expert copying to user code (#29943) 
* ggml: refactor selective expert copying to user code

* tests: enroll two models into selective expert copy test

* tests: use deepseek2 as test model

* improve comment in ggml-backend.h

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

* cont: fix whitespace

* cont : better comments

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-10-06 10:59:45 +03:00
Concedo
4d27749c93 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-ibm.yml
#	.github/workflows/ci-self-hosted-cuda.yml
#	.github/workflows/release.yml
#	.github/workflows/server-self-hosted.yml
#	AGENTS.md
#	README.md
#	ci/run.sh
#	docs/autoparser.md
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/development/HOWTO-add-model.md
#	docs/function-calling.md
#	docs/ops.md
#	docs/ops/CPU.csv
#	ggml/CMakeLists.txt
#	ggml/src/ggml-blas/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/amx/amx.cpp
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cuda/CMakeLists.txt
#	ggml/src/ggml-et/ggml-et.cpp
#	ggml/src/ggml-hexagon/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/allreduce-ops.c
#	ggml/src/ggml-hexagon/htp/allreduce-ops.h
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/work-queue.c
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/fattn-common.hpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	ggml/src/ggml-virtgpu/ggml-backend-buffer-type.cpp
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	pyproject.toml
#	scripts/snapdragon/run.py
#	skills/code-review/SKILL.md
#	tests/fusion/MTL.csv
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tests/test-model-resolution.cpp
#	tests/test-quantize-fns.cpp
#	tests/test-recurrent-state-rollback.cpp
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/CMakeLists.txt
#	tools/server/README.md
 2026-10-03 17:59:14 +08:00
Georgi Gerganov
631109b34d
ggml : add alloc_buffer_n to buffer type interface (#23671) 
* ggml : add `alloc_buffer_n` to buffer type interface

Add alloc_buffer_n method to ggml_backend_buffer_type_i
interface, with a public API ggml_backend_buft_alloc_buffer_n.

- Default implementation in ggml-backend.cpp handles multi-buffer
  splitting and tensor allocation via ggml_tallocr
- Meta buffer type provides custom implementation that creates
  per-device sub-contexts and delegates to simple buffer types
- ggml_backend_alloc_ctx_tensors_from_buft now collects tensors
  into a list and delegates to the new API
- Remove temporary ggml_backend_meta_alloc_ctx_tensors_from_buft
- Add NULL alloc_buffer_n to all existing buffer type
  interfaces (cpu, metal, openvino, hexagon, webgpu, zdnn, virtgpu, repack)

Assisted-by: llama.cpp:local pi

* cont : fix `cur_buf_size` init after flushing a buffer

* ggml : add TODO tag for shared buffer split logic

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* tests : add alloc_buffer_n coverage

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* cont : fix compile warnings

* tests : add descriptions for alloc_buffer_n tests

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* ggml : address review comments on alloc_buffer_n

- restore GGML_LOG_ERROR on buffer alloc / tensor init failure in the
  default impl (name the failing tensor)
- check the malloc result and drop the _impl indirection in
  ggml_backend_alloc_ctx_tensors_from_buft
- remove comments that restate the code
- fix the TAG_ALLOC_SHARED_BUFFER_SPLIT typo

Assisted-by: pi:llama.cpp/Qwen3.8-27B

* ggml : add get_alloc_size_n to buffer type interface

- Add ggml_backend_buft_get_alloc_size_n public API
- Add optional get_alloc_size_n callback to ggml_backend_buffer_type_i
- Share tensor->buffer planning between alloc_buffer_n default and get_alloc_size_n default
- Replace unchecked realloc with std::vector in alloc_buffer_n default
- Make ggml_backend_alloc_ctx_tensors_from_buft_size use the new API
- Add test-alloc coverage for get_alloc_size_n

Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp

* cont : report malloc failure
 2026-10-02 11:08:08 +03:00
Johannes Gäßler
78e2964c23
llama: refer to segment documentation [no ci] (#29074) 2026-10-01 21:52:40 +02:00
Aaron Teo
cee37ffea0
ci: add zdnn backend build but not test (#29541) 
* ci: add zdnn backend build but not test

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ci: attempt to run a ubuntu 26.04 container

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ci: set shell to bash

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ci: clean up comments

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* ggml-zdnn: fix compiler errors

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

* vendor: attempt to ignore warnings from vendored files

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>

---------

Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
 2026-09-29 20:45:14 +03:00
Georgi Gerganov
e97545d916 sycl : fix compile warnings 2026-09-23 11:47:24 +03:00
Łukasz Ślusarczyk
af911149c5
sycl : pinned memory use right device context instead of 0 (#28895) 2026-09-21 13:58:59 +03:00
Wagner Bruna
469f456003
sd: sync with master-852-14eddb3 (#2457) 
* bump GGML_MAX_NAME to 160

https://github.com/leejet/stable-diffusion.cpp/pull/1950

* sd: sync with master-852-14eddb3

* fix int8 and fp8 tensor size validation

* temporarily disable LoRA caching
 2026-09-19 17:20:14 +08:00
Concedo
d1c93e8e89 Merge commit 'c9a5eeeb34' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/check-vendor.yml
#	.github/workflows/pre-tokenizer-hashes.yml
#	.github/workflows/python-check-requirements.yml
#	.github/workflows/python-lint.yml
#	.github/workflows/python-type-check.yml
#	.github/workflows/update-ops-docs.yml
#	CODEOWNERS
#	ggml/include/ggml-sycl.h
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-mm-kernels-flat.h
#	ggml/src/ggml-hexagon/htp/hvx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/fusion.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/ssm_conv.cpp
#	ggml/src/ggml-sycl/ssm_conv.hpp
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/llama-bench/llama-bench.cpp
 2026-09-19 10:10:02 +08:00
Michael Taylor
aa39d7a3e1
[SYCL] Fix function signature for ggml_backend_sycl_split_buffer_type (#28981) 2026-09-16 22:15:47 -04:00
Aman Gupta
37b53fd454
qwen4exp: add hc ops (#28901) 2026-09-16 16:00:01 +08:00
Concedo
802810260d Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.ecrc
#	.github/actions/get-tag-name/action.yml
#	.github/actions/windows-setup-cuda/action.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	.github/workflows/server-self-hosted.yml
#	CONTRIBUTING.md
#	app/CMakeLists.txt
#	ci/run.sh
#	docs/backend/OPENVINO.md
#	docs/ops.md
#	docs/ops/CUDA.csv
#	examples/eval-callback/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/moe_reorder_b.cl
#	ggml/src/ggml-opencl/kernels/ssm_scan.cl
#	ggml/src/ggml-openvino/ggml-decoder.cpp
#	ggml/src/ggml-openvino/ggml-decoder.h
#	ggml/src/ggml-openvino/ggml-openvino-extra.cpp
#	ggml/src/ggml-openvino/ggml-openvino-extra.h
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-openvino/ggml-quants.cpp
#	ggml/src/ggml-openvino/ggml-quants.h
#	ggml/src/ggml-openvino/openvino/frontend.cpp
#	ggml/src/ggml-openvino/openvino/node_context.h
#	ggml/src/ggml-openvino/openvino/op/add.cpp
#	ggml/src/ggml-openvino/openvino/op/diag.cpp
#	ggml/src/ggml-openvino/openvino/op/div.cpp
#	ggml/src/ggml-openvino/openvino/op/glu_geglu_quick.cpp
#	ggml/src/ggml-openvino/openvino/op/glu_swiglu.cpp
#	ggml/src/ggml-openvino/openvino/op/mul_mat_id.cpp
#	ggml/src/ggml-openvino/openvino/op/mulmat.cpp
#	ggml/src/ggml-openvino/openvino/op/norm.cpp
#	ggml/src/ggml-openvino/openvino/op/pad.cpp
#	ggml/src/ggml-openvino/openvino/op/permute.cpp
#	ggml/src/ggml-openvino/openvino/op/rope.cpp
#	ggml/src/ggml-openvino/openvino/op/set_rows.cpp
#	ggml/src/ggml-openvino/openvino/op/transpose.cpp
#	ggml/src/ggml-openvino/openvino/op/unary_softplus.cpp
#	ggml/src/ggml-openvino/openvino/op_table.cpp
#	ggml/src/ggml-openvino/openvino/op_table.h
#	ggml/src/ggml-openvino/openvino/pass/squeeze_matmul.cpp
#	ggml/src/ggml-openvino/openvino/translate_session.cpp
#	ggml/src/ggml-openvino/utils.cpp
#	ggml/src/ggml-openvino/utils.h
#	scripts/hip/gcn-cdna-vgpr-check.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/server/CMakeLists.txt
#	tools/tuning/CMakeLists.txt
 2026-09-16 15:32:56 +08:00
Patrick Hoffmann
7609846557
rpc : hash-cache only weights (#28789) 
* rpc : hash-cache only weights

ggml_backend_rpc_buffer_set_tensor and ggml_backend_rpc_set_tensor_async
hashed every transfer above HASH_THRESHOLD and let `rpc-server -c` serve it
from its file cache. The cache is meant for weights, but the activations
ggml_backend_sched copies between backends took the same path: with a
two-node split of Qwen3.8-Flash-Next every prefill ubatch above 10 MB was
hashed, written to the worker's cache directory (1.4 TB after a day) and
later served from there. Use the hash path only for tensors in buffers
marked GGML_BACKEND_BUFFER_USAGE_WEIGHTS.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

* rpc : save a cache entry only for the tensor that missed the hash check

With the client hashing weights only, the server still wrote every
SET_TENSOR above HASH_THRESHOLD to the cache directory, so the compute
data the scheduler sends kept filling the disk. Remember the hash of the
last SET_TENSOR_HASH that missed and save only the SET_TENSOR that
follows it with that hash - the weight the client is re-sending.

* rpc : signal the cache decision in the SET_TENSOR payload

Replace the server-side `pending_cache` state with a `cache_flag` byte
in the SET_TENSOR message: the client sets it when SET_TENSOR_HASH
reported a miss, the server saves a cache entry only when it is set.
Bump RPC_PROTO_MAJOR_VERSION since the wire format changes.

---------

Co-authored-by: Patrick Hoffmann <patrickhoffmann@MacBook-Pro-14-HOP.local>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
 2026-09-15 14:50:20 +03:00
Concedo
ad30a3cc99 Merge commit '7d701b5929' into concedo_experimental 
# Conflicts:
#	.github/workflows/python-type-check.yml
#	examples/pydantic_models_to_grammar.py
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-arith.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/conv2d.cl
#	ggml/src/ggml-opencl/kernels/conv2d_f16_f32.cl
#	scripts/jinja/jinja-tester.py
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/tool_bench.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-recurrent-state-rollback.cpp
 2026-09-09 10:19:55 +08:00
Georgi Gerganov
5a6caa05fc
ggml : update ggml_prec specification (#26675) 
* ggml : update ggml_prec specification

[no ci]

* cont : add GGML_PREC_BF16

* cont : rework API

* cont : use new API

* cont : swap arg order

* cont : support for MUL_MAT_ID

* cont : fix accidental remove of "break;"

* cont : return bools, add doc TAG_GGML_PREC, clean-up

* cont : add search tag

* cont : ws
 2026-09-08 09:06:24 +03:00
Concedo
f64ab79adf Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-wasm.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/hip-quality-check.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	docs/backend/SYCL.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/concat.cl
#	ggml/src/ggml-opencl/kernels/cpy.cl
#	ggml/src/ggml-sycl/common.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/fattn-buffers.cpp
#	ggml/src/ggml-sycl/fwht.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
 2026-09-05 12:09:30 +08:00
Georgi Gerganov
64a155d242
sync : ggml (#28379) 
* ggml : rename and make private ggml_op_alloc_size_may_expand() (ggml/0)

cont https://github.com/ggml-org/llama.cpp/pull/27960

* ggml : bump version to 0.23.0 (ggml/1618)

* sync : ggml
 2026-09-04 14:39:19 +03:00
Concedo
2e04e6509d Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-msys.yml
#	.github/workflows/build-opencl.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-riscv.yml
#	.github/workflows/build-sanitize.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-wasm.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/copilot-setup-steps.yml
#	.github/workflows/hip-quality-check.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	CODEOWNERS
#	build-xcframework.sh
#	docs/android.md
#	docs/backend/SYCL.md
#	docs/build.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-opnode.h
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tests/test-save-load-state.cpp
#	tools/mtmd/CMakeLists.txt
 2026-09-02 23:24:09 +08:00
Aman Gupta
8e93a9773b
CUDA + ggml: add sparse-fa for DSV4/GLM (#27970) 2026-09-02 17:27:37 +03:00
Concedo
c22d6e5c35 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-et/et-kernels/src/glu_f32.c
#	ggml/src/ggml-et/ggml-et-cpu-compare.cpp
#	ggml/src/ggml-et/ggml-et-ops.cpp
#	ggml/src/ggml-et/ggml-et.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/glu.cl
#	ggml/src/ggml-openvino/openvino/op/glu_swiglu.cpp
#	ggml/src/ggml-openvino/openvino/op_table.cpp
#	ggml/src/ggml-openvino/openvino/op_table.h
#	ggml/src/ggml-rpc/CMakeLists.txt
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/glu.wgsl
#	scripts/sync_vendor.py
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/CMakeLists.txt
#	tools/server/README.md
 2026-08-31 18:39:16 +08:00
Aman Gupta
0190529ec4
ggml: add SWIGLU_CLAMP (#27930) 
* ggml: add SWIGLU_CLAMP

* add vulkan shader
 2026-08-30 23:00:02 +08:00
Georgi Gerganov
73f56d105b
ggml : add ggml_backend_op_alloc_size_may_expand, use it in RPC (#27960) 
some backends (Metal, SYCL, WebGPU) require additional memory for
fleeting data for certain ops, which is reflected in their
get_alloc_size implementations.

add ggml_backend_op_alloc_size_may_expand() to the backend utils,
listing these ops, and assert in ggml_backend_buft_get_alloc_size
that a backend expanding the alloc size of a compute op only does so
for ops listed in the helper.

use the helper in the RPC backend to decide whether to query the
remote server for the actual alloc size, instead of a hardcoded list.

Assisted-by: pi:llama.cpp/Qwen3.8-27B
 2026-08-30 09:17:47 +03:00
Concedo
ae60e1d6e0 Merge commit 'deae5ee133' into concedo_experimental 
# Conflicts:
#	.devops/openvino.Dockerfile
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/docker.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/ui-build-self-hosted.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui-publish.yml
#	.github/workflows/ui-self-hosted.yml
#	.github/workflows/ui.yml
#	CMakeLists.txt
#	docs/backend/snapdragon/CMakeUserPresets.json
#	docs/backend/snapdragon/README.md
#	docs/backend/snapdragon/developer.md
#	docs/backend/snapdragon/linux.md
#	docs/backend/snapdragon/windows.md
#	docs/ops.md
#	docs/ops/Vulkan.csv
#	ggml/cmake/ggml-config.cmake.in
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-opnode.h
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-arith.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-rpc/CMakeLists.txt
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/README.md
#	tools/server/README.md
#	tools/ui/tests/stories/a11y/ChatScreenForm.a11y.stories.svelte
 2026-08-28 19:31:29 +08:00
Radoslav Gerganov
d0132a680a
rpc : implement event and async backend APIs (#18626) 
* rpc : implement event and async backend APIs

* cache responses from RPC_CMD_GET_ALLOC_SIZE
 2026-08-26 17:34:46 +03:00
Concedo
4447017602 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/actions/ccache-clear/action.yml
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-opencl.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-wasm.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/hip-quality-check.yml
#	.github/workflows/server.yml
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	common/CMakeLists.txt
#	common/chat.cpp
#	docs/autoparser.md
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/flash_attn_vec_split.wgsl
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/peg-parser/test-json-serialization.cpp
#	tests/peg-parser/tests.h
#	tests/test-chat-auto-parser.cpp
#	tests/test-chat-peg-parser.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-jinja.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tests/test-llama-archs.cpp
#	tests/test-model-resolution.cpp
#	tests/test-recurrent-state-rollback.cpp
#	tools/CMakeLists.txt
 2026-08-25 20:44:34 +08:00
Georgi Gerganov
6036c635e2
ggml : fix ggml_clamp (#27644) 
* ggml : fix ggml_clamp

* cont : update ggml-alloc
 2026-08-24 10:43:04 +03:00
Concedo
8c732ca2cc Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.devops/openvino.Dockerfile
#	.github/actions/windows-setup-cuda/action.yml
#	.github/workflows/build-cache.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/docker.yml
#	.github/workflows/make-release.yml
#	.github/workflows/release.yml
#	AUTHORS
#	CMakeLists.txt
#	README.md
#	build-xcframework.sh
#	ci/run.sh
#	common/CMakeLists.txt
#	docs/backend/OPENVINO.md
#	examples/gguf-hash/CMakeLists.txt
#	examples/gguf-hash/gguf-hash.cpp
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-et/ggml-et.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32.cl
#	ggml/src/ggml-opencl/kernels/moe_sort_by_expert.cl
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/common_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_subgroup_matrix.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec_acc.tmpl
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/mtmd-helper.cpp
#	tools/perplexity/perplexity.cpp
#	tools/server/README.md
#	tools/ui/src/lib/hooks/use-tools-panel.svelte.ts
#	vendor/hash/CMakeLists.txt
 2026-08-21 23:27:27 +08:00
Xuan-Son Nguyen
fe8156f789
ggml: add ggml_rope_set_offset (+ metal support) (#27120) 
* add params

* cpu kernel

* metal kernel

* add test backend ops

* gate other backends

* ggml: (cuda) support ggml_rope_set_offset (#27121)

* rm cuda supports_op guard, fix webgpu clang-format

* ggml: support ggml_rope_set_offset on vulkan (#27344)

* ggml: support ggml_rope_set_offset on vulkan

* remove inplace optimization
 2026-08-19 14:04:57 +02:00
Aman Gupta
af5172627d
RPC: populate use_count to enable fusion inside backends (#27142) 
* RPC: populate use_count to enable fusion inside backends

* bump minor version
 2026-08-18 21:08:57 +05:30
Concedo
82e15c08bf Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/developer.md
#	examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
#	examples/sycl/run-llama2.sh
#	examples/sycl/start-svr.sh
#	examples/sycl/test.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-start-svr.bat
#	examples/sycl/win-test.bat
#	ggml/CMakeLists.txt
#	ggml/src/ggml-et/et-kernels/src/ssm_scan_f32.c
#	ggml/src/ggml-et/ggml-et-ops.cpp
#	ggml/src/ggml-et/ggml-et-ops.h
#	ggml/src/ggml-sycl/ssm_scan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	scripts/bench-models.sh
#	scripts/snapdragon/adb/run-bench.sh
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-mtmd.sh
#	scripts/snapdragon/windows/run-bench.ps1
#	scripts/snapdragon/windows/run-cli.ps1
#	scripts/snapdragon/windows/run-completion.ps1
#	scripts/snapdragon/windows/run-mtmd.ps1
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/README.md
#	tools/server/README.md
 2026-08-15 22:50:04 +08:00
lnigam
1692f9e50b
ggml : recurrent state rollback for ggml_ssm_scan (#26623) 
* Initial changes for Recurrent state rollback for nemotron for cpu and cuda

* Removing CPU RS rollback. Will enable it in subsequent PRs

* addition of test case

* Removing assert and calling runtime API to check if op is supported

* removing extra API and updating the call sites for K

* replace static cuda detection to runtime fused_op api

* address review comments and fallback when SSM rollback not supprted

* Adding changes for supporting RS-rollback in CPU. Also added test-backend-ops for cpu and cuda

* removing memory manipulation as rs rollback is now supported in CPU

* removing the static probe which is not needed now

* correcting the format

* address review comments

* enabling test for all the backends, unsupported backends will fallback to CPU

* Apply suggestions from code review

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

* choose different graph based on the result of fused_ssm_op is supported or not and also handled memory->n_rs_seq >1 case incase of op is not supported

* Support K > 1 in ssm_scan for all backends

* Fix CI Issues

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
 2026-08-14 17:20:40 +03:00
Concedo
dcfe29317e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/actions/windows-setup-rocm/action.yml
#	.github/workflows/build-cache.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/release.yml
#	.github/workflows/server-sanitize.yml
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/server.yml
#	ci/run.sh
#	docs/speculative.md
#	examples/lookup/lookup.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-et/ggml-et.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q4_0.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q8_0.cl
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-virtgpu/backend/backend-dispatched-device.cpp
#	ggml/src/ggml-virtgpu/backend/shared/api_remoting.h
#	ggml/src/ggml-virtgpu/ggml-backend-buffer-type.cpp
#	ggml/src/ggml-virtgpu/ggml-backend-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward-device.cpp
#	ggml/src/ggml-virtgpu/virtgpu-forward.gen.h
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
#	ggml/src/ggml-zdnn/ggml-zdnn.cpp
#	ggml/src/ggml-zendnn/ggml-zendnn.cpp
#	tests/peg-parser/test-json-parser.cpp
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
 2026-08-11 15:13:15 +08:00
Ruben Ortlam
153d324bcf
llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)
Some checks failed
Python Type-Check / python type-check (push) Has been cancelled
Details 
* llama: add new default load-mode auto which picks mmap unless a non-Metal iGPU is used

* Update ggml/src/ggml-hexagon/ggml-hexagon.cpp

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>

* set mmap_support to false on OpenCL backend

* fix order of load modes

* use -1 for auto

* resolve load mode auto earlier to correctly pick gpu host or cpu memory

* add load mode auto to llama-bench

* bump virtgpu api version, regenerate docs

---------

Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
 2026-08-11 09:20:46 +03:00
Concedo
8a16f96307 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	SECURITY.md
#	build-xcframework.sh
#	ci/run.sh
#	docs/development/HOWTO-add-model.md
#	examples/model-conversion/scripts/causal/convert-model.sh
#	examples/model-conversion/scripts/embedding/convert-model.sh
#	scripts/sync_vendor.py
#	scripts/ui-assets.cmake
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-grammar-parser.cpp
#	tests/test-llama-archs.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/mtmd.h
#	tools/mtmd/tests/test-deepseek-ocr.py
#	tools/server/README.md
#	tools/tts/CMakeLists.txt
#	tools/tts/convert_pt_to_hf.py
 2026-08-07 20:46:56 +08:00
Pascal
c8e03ce812
mtmd/ggml: add ggml_build_forward_order (#26649) 
* ggml: add ggml_build_forward_order

ggml_build_forward_expand marks the tensor and all its ancestors for
compute, so using it as a pure ordering hint (keeping q, k and v
together) defeats ggml_build_forward_select: the unselected branch is
forced to run with inputs that were never uploaded. In the mtmd audio
graph this makes GEN_WAV calls execute the GEN_CODE branch with a
stale inp_code0, hitting the get_rows bound assert on CPU.

Add ggml_build_forward_order, which inserts nodes without the compute
flag; the flag is restored when the branch is actually selected.
Switch the q/k/v hints in clip_graph::build_attn to it.

* nit: reduce comments (AGENTS.md)
 2026-08-06 00:47:59 +02:00
Concedo
98926f27c1 Merge commit '11b068d066' into concedo_experimental 
# Conflicts:
#	CONTRIBUTING.md
#	docs/backend/SYCL.md
#	docs/install.md
#	docs/speculative.md
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/fattn-onednn.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/glu.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
 2026-07-31 17:06:19 +08:00
Aman Gupta
f5b9bd39b5
RPC: add tensor_memset (#25912) 2026-07-29 15:04:30 +08:00
Concedo
0a0b88a5c0 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/backend/OPENCL.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp-drv.h
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	ggml/src/ggml-hexagon/htp/binary-ops.c
#	ggml/src/ggml-hexagon/htp/cumsum-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hex-profile.h
#	ggml/src/ggml-hexagon/htp/hex-utils.h
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/hmx-queue.c
#	ggml/src/ggml-hexagon/htp/hmx-queue.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/rope-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemm_moe_mxfp4_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q4_0_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q4_k_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q6_k_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemm_moe_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemm_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemm_noshuffle_q4_k_q8_1_dp4a.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_q4_k_f32_flat.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_q5_k_f32_flat.cl
#	ggml/src/ggml-sycl/dmmv.cpp
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/sync-ggml.last
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tests/test-recurrent-state-rollback.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
 2026-07-18 12:26:15 +08:00
Aman Gupta
0dc74e332e
DeepseekV4: Add fused hyper-connection ops (#25585) 
* dsv4 hc-ops

* add missing files;

* add cparams

* update rpc version

* address review comments

* address review comments
 2026-07-17 00:33:33 +08:00
Rajendra Matcha
f15bd60901
kleidiai: Add SME vs SME2 distinction in kernel dispatch (#25478) 
The current integration treats SME as a single capability (CPU_FEATURE_SME)
with no distinction between SME(v1) and SME2. The kernels dispatched under
CPU_FEATURE_SME use SME2-specific instructions, making dispatch incorrect
on SME(v1)-only hardware.

We introduce build-time and runtime distinction between SME and SME2, and
wire SME(v1) and SME2 kernels based on actual hardware support.
 2026-07-16 08:57:04 -07:00
Concedo
9001369da0 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-cpu/ops.cpp
#	ggml/src/ggml-cuda/mmq.cuh
#	ggml/src/ggml-hexagon/htp/hmx-queue.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_iq4_nl_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q1_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_0_f32_spec.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_1_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_0_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_1_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q5_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q6_k_f32.cl
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q8_0_f32.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f16.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f32.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f32_1row.cl
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	tests/test-backend-ops.cpp
#	tests/test-chat-auto-parser.cpp
#	tests/test-export-graph-ops.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/tokenize/tokenize.cpp
 2026-07-15 15:39:31 +08:00
fairydreaming
a7312ae94f
ggml : add a set of functions for checking contiguity of inner tensor dimensions (#25650) 
Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
 2026-07-14 14:37:52 +02:00
Concedo
fa21872f97 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	docs/backend/SYCL.md
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/gemv_moe_mxfp4_f32_ns.cl
#	ggml/src/ggml-opencl/kernels/gemv_moe_q4_k_f32_ns.cl
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-alloc.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-gguf.cpp
#	tests/test-save-load-state.cpp
 2026-07-13 20:53:37 +08:00
QuintinShaw
ad8d821991
gguf : add tensor shape accessor (#24405) 
* gguf : add tensor shape accessors

* gguf : return tensor shape as const int64_t *

* gguf : remove n_dims accessor, keep only gguf_get_tensor_ne
 2026-07-13 13:55:15 +03:00
fairydreaming
00f5442cc4
ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231) 
* ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer

* ggml : remove scale parameters from lightning indexer OP, add f16 mask parameter

* tests : add GGML_OP_LIGHTNING_INDEXER tests

* ggml : bump RPC version

* chore : check if lightning indexer input tensors are not transposed

* tests : count flops instead of bandwidth in lightning indexer test

* chore : add missing const

* chore : whitespace

* ggml : renamed variables in CPU lightning indexer implementation

* ggml : fix lightning indexer mask broadcasting

* tests : tests for lightning indexer mask broadcasting

* chore : whitespace

* llama : use GGML_OP_LIGHTNING_INDEXER in DeepSeek V3.2 and DeepSeek V4 models

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
 2026-07-11 11:39:07 +02:00
Concedo
f57cd915a9 Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	.github/workflows/ui-publish.yml
#	CODEOWNERS
#	docs/ops.md
#	ggml/CMakeLists.txt
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	scripts/sync-ggml.last
#	tools/mtmd/tests/test-deepseek-ocr.py
 2026-07-11 11:36:59 +08:00
Concedo
0f0245161e Merge branch 'upstream' into concedo_experimental 
# Conflicts:
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	tests/test-backend-ops.cpp
#	tests/test-quantize-fns.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
 2026-07-11 09:20:40 +08:00
Concedo
fc6e197fdd Merge commit '33ca0dcb9d' into concedo_experimental 
# Conflicts:
#	docs/backend/SYCL.md
#	docs/build.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-cuda/ggml-cuda.cu
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-opencl/fa_tune.h
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/flash_attn_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q4_0.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_q8_0.cl
#	ggml/src/ggml-opencl/kernels/mul_mv_f16_f32_l4.cl
#	ggml/src/ggml-sycl/backend.hpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/cpy.cpp
#	ggml/src/ggml-sycl/cpy.hpp
#	ggml/src/ggml-sycl/dmmv.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/presets.hpp
#	src/llama-graph.cpp
#	src/llama-kv-cache.cpp
 2026-07-11 08:46:16 +08:00