* ggml : add ggml_set_rows

Add ggml_set_rows(a, b, c) which copies rows from 'b' into 'a' using
indices from 'c'.

ref: ggml-org#8366

* use I64 for indices

* ggml : add repeat impl for i64

* ggml : add ggml_is_contiguous_rows

* ggml : ggml_set_rows support broadcast

* ggml : ggml_set_rows support quantized dst

ggml-ci

* ggml : support GGML_TYPE_F32 ".from_float" trait

* ggml : ggml_set_rows update comment + better index name

* tests : add ggml_set_rows

* metal : add ggml_set_rows implementation

ggml-ci

* ggml : simplify forward_dup_f32

* ggml : fix supports_op

* tests : add comment to set_rows

* ggml : leave the repeat_i64 for a separate PR

ggml-ci

* ggml : set_rows use std::min instead of MIN

* ggml : better error message for set_rows unsupported type

* metal : perform op->type check only once

* tests : more consistent implementation + more tests

ggml-ci

---------

Co-authored-by: Georgi Gerganov <[email protected]>

ggml-ci

ggml-ci

This setting needs to be passed through to vulkan-shaders-gen

Add Day-0 support for Baidu ERNIE 4.5 0.3B model.

Signed-off-by: Weizhao Ouyang <[email protected]>

ggml-org#14378)

)

* CUDA: add bf16 and f32 support to cublas_mul_mat_batched

* Review: add type traits and make function more generic

* Review: make check more explicit, add back comments, and fix formatting

* Review: fix formatting, remove useless type conversion, fix naming for bools

* vulkan: Add fusion support for RMS_NORM+MUL

- Add a use_count to ggml_tensor, so we can detect if an output is used more than once.
- Change the ggml-vulkan rms_norm shader to optionally multiply by another tensor.
- Add detection logic and basic fusion logic in ggml-vulkan.
- Add some testing support for fusion. Rather than computing one node at a time, allow
for computing the whole graph and just testing one node's results. Add rms_norm_mul tests
and enable a llama test.

* extract some common fusion logic

* fix -Winconsistent-missing-override

* move ggml_can_fuse to a common function

* build fix

* C and C++ versions of can_fuse

* move use count to the graph to avoid data races and double increments when used in multiple threads

* use hash table lookup to find node index

* change use_counts to be indexed by hash table slot

* minimize hash lookups

style fixes

* last node doesn't need single use.
fix type.
handle mul operands being swapped.

* remove redundant parameter

---------

Co-authored-by: slaren <[email protected]>

* implement unary REGLU/GEGLU/SWIGLU cpu ops

* relax constraints

* duplicate shape of source

* fix ggml_vec_geglu_f16

* special case gated ops

* implement unary REGLU/GEGLU/SWIGLU cuda ops

* tighten constraints again

* refactor into GGML_GLU_OP

* metal : add glu kernels

ggml-ci

* add CUDA_GLU_BLOCK_SIZE [no ci]

* more constraints and use 64bit ints

ggml-ci

* 64bit multiplication [no ci]

* implement swapped variants (cpu/cuda)

* update comment [no ci]

ggml-ci

* Vulkan: Add GLU ops and shaders

* SYCL: Implement fused kernel GEGLU, SWIGLU and REGLU for single up+gate

* ggml : implement GLU for split up/gate (ggml-org#14181)

* implement GLU for split up/gate

* add tests for ggml_glu_split

* Vulkan: Implement glu_split logic and shader support

* add split to logging [no ci]

* SYCL: refactor element_size ops and add split up and gate support to gated kernels

* SYCL: switch GEGLU to use tanh approximation

---------

Co-authored-by: 0cc4m <[email protected]>
Co-authored-by: Akarshan <[email protected]>

* GGML: increase OP count in assertion

* Refactor: Optimize SYCL element-wise operations with unary function inlining

This commit refactors the SYCL element-wise operations to improve performance by:

- Inlining unary operations (sgn, abs, elu, gelu, silu, etc.) to reduce kernel launch overhead.
- Introducing helper functions `op_xxx` for each unary operation to encapsulate the logic.
- Replacing direct kernel calls with calls to these inlined functions.
- Using `__dpct_inline__` to encourage compiler inlining.
- Minor code cleanup and consistency improvements.

The changes aim to reduce kernel launch overhead and improve the overall efficiency of element-wise operations on SYCL devices.

* vulkan: Increase workgroup size for GLU, for performance (ggml-org#14345)

* vulkan: Increase workgroup size for GLU, for performance

* vulkan: change GLU shaders to do one element per invocation rather than one row per workgroup

* merge fix

* metal : add support for split and swap

ggml-ci

---------

Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: 0cc4m <[email protected]>
Co-authored-by: Akarshan <[email protected]>
Co-authored-by: Jeff Bolz <[email protected]>

* SYCL: disable faulty fp16 CPU exponent for now

* Revert "SYCL: disable faulty fp16 CPU exponent for now"

This reverts commit ed0aab1.

* SYCL: disable faulty fp16 CPU exponent for now

* Fix logic of disabling exponent kernel

…ml-org#14322)

…eature), from command line and from client (ggml-org#13196)

* initial commit for handling extra template kwargs

* enable_thinking and assistant prefill cannot be enabled at the same time

* can set chat_template_kwargs in command line

* added doc

* fixed formatting

* add support for extra context in generic template init

* coding standard: common/chat.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* coding standard:  common/chat.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* Apply suggestions from code review

coding standard: cosmetic changes

Co-authored-by: Georgi Gerganov <[email protected]>

* fix merge conflict

* chat.cpp: simplify calls to apply to ensure systematic propagation of extra_context (+ the odd existing additional_context)

* normalize environment variable name

* simplify code

* prefill cannot be used with thinking models

* compatibility with the new reasoning-budget parameter

* fix prefill for non thinking models

---------

Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: Olivier Chafik <[email protected]>

* Update docker.yml

修改docker.yml文件中的内容使其停止周期性的运行该workflow，如果想要运行该workflow可以手动启动

* Remove redundant include path in CMakeLists.txt

The parent directory '..' was removed from the include directories for the ggml-cpu-feats target, to avoid unnecessary include paths.

* Enable scheduled Docker image builds

Uncomments the workflow schedule to trigger daily Docker image rebuilds at 04:12 UTC, improving automation and keeping images up to date.

* metal : disable fast-math for some cpy kernels

ggml-ci

* cont : disable for q4_1

ggml-ci

* cont : disable for iq4_nl

ggml-ci

ggml-ci

* Conv2D: Add CPU version

* Half decent

* Tiled approach for F32

* remove file

* Fix tests

* Support F16 operations

* add assert about size

* Review: further formatting fixes, add assert and use CPU version of fp32->fp16

This commit renames the variable `best_mad` to `best_error` in the
`make_qkx2_quants` function.

The motivation for this is that the name `best_mad` can be somewhat
confusing if mean absolute deviation (MAD) is not in use.

* add "align corners" mode for bilinear upscale, and allow downscaling
* add ggml_interpolate, deprecate ggml_upscale_ext, pass in align-corners as bit-flag
* test-backend-ops: replace ggml_upscale_ext with ggml_interpolate, add test cases for downscale and align-corners

ggml-ci

* ggml : add version function to get lib version

This commit adds a function `ggml_version()` to the ggml library that
returns the version of the library as a string.

The motivation for this is that it can be useful to be able to
programmatically check the version of the ggml library being used.

Usage:
```c
printf("GGML version: %s\n", ggml_version());
```
Output:
```console
GGML version: 0.0.2219
```

* ggml : add ggml_commit()

---------

Co-authored-by: Georgi Gerganov <[email protected]>

ggml-ci

* llama : initial Mamba-2 support

* ggml : SIMD ggml_ssm_scan for Mamba-2

* ggml : improve ggml_mul speed when masking recurrent states

* llama : support running Mamba-Codestral-7B-v0.1

* llama : fix Mamba-2 conv state saving

* ggml : make the ggml_mul fast broadcast path more consistently formatted

* llama : remove unused variable

* llama : add missing break

* convert_hf : prefer SentencePiece tokenizer for Mamba-2 when present

The tokenzier.json of Mamba-Codestral-7B-v0.1 otherwise requires
workarounds to work correctly.

* llama : avoid redundant state copy for Mamba 1 and 2

* metal : attempt to adapt SSM_SCAN for Mamba-2

* metal : fix SSM_SCAN pipeline scope

* metal : use log and exp instead of log1pf and expf in SSM_SCAN

* metal : remove unused arguments for SSM_SCAN

The max index is 31, so trimming the arguments is necessary.

* metal : add back n_seqs to SSM_SCAN args

Whoops, this is needed for the offset in the concatenated output.

* metal : fix SSM_SCAN state head offset

* metal : fix wrong number of tokens per sequence in SSM_SCAN

* ggml : remove unused fast broadcast path in GGML_MUL

This was initially added because states were masked with ggml_mul,
but this is no longer done and so this "optimisation" is no longer
necessary, or at least not worth the additional code complexity.

* ggml : avoid multiply by D in GGML_OP_SSM_SCAN

This makes the weight buft detection in src/llama.cpp simpler.

* convert : transpose Mamba-2 A, D and reshape SSM_NORM

This breaks existing conversions of Mamba-2 models
to avoid some reshapes.

Not sure if it's a good idea,
but it makes the graph slightly cleaner.

* llama : more appropriate SSM_SCAN and SSM_CONV buft support checks

* convert : fix flake8 lint

* metal : fix confusion between ; and ,

* metal : add missing args for nb references in ssm_scan_f32_group

* metal : single-user mamba2 inference works

* kv-cache : remove const_cast when setting inputs for s_copy

And also fix multi-user inference for recurrent models
by using cell_id instead of i as the kv cell index
when populating s_copy.

* convert : avoid AutoConfig for Mamba and Mamba2 hparams

* kv-cache : allow context shift for recurrent models

* graph : fix recurrent state copies when avoiding copies

Works, but using lambda functions might not be that clean.

* ggml : fix mamba2 ssm scan when compiled with SVE

* ggml-cpu : reorder SVE FMA for consistency with other SIMD arches

* cuda : implement ssm scan for Mamba2

There is still room for improvement, but it works!

* cuda : adapt Mamba1 ssm scan to shape changes from Mamba2

* mamba : fix mismatched new and delete size for llm_build_mamba

Subclasses of llm_graph_context cannot have extra fields,
because the called destructor is not the one from the subclass.
This otherwise would cause problems when runnning Mamba-(1|2) inference
when compiled -DGGML_SANITIZE_ADDRESS=ON

* cuda : graceful fallback for Mamba-1 models with weird embd size

* add support for chat template jinja files

* remove gemma3n hack

…-org#14497)

ggml-ci

* ggml : fix FA mask dim 2 and 3

ggml-ci

* backends : unsupport batched FA in CUDA and Vulkan

ggml-ci

* vulkan : disable FA for mask->ne[2] != 1

* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci

* convert : correct gemma 3n conversion

* rm redundant code

…g#14504)

Signed-off-by: nscipione <[email protected]>

* vulkan: better parameterize FA by head sizes

* vulkan: support mixed/deepseekR1 FA head sizes

…g#14002)

Co-authored-by: luyuhong <[email protected]>

ggml-ci

ggml-ci

ggml-ci

ggml-ci

…14368)

* test-backend-ops: add support for specifying output format

Signed-off-by: Xiaodong Ye <[email protected]>

* Address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

* Add build_commit and build_number in test_result

Signed-off-by: Xiaodong Ye <[email protected]>

* Address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

* refactor

Signed-off-by: Xiaodong Ye <[email protected]>

* Get build commit from ggml_commit()

Signed-off-by: Xiaodong Ye <[email protected]>

* Merge errors into test_operation_info && address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

* Address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

* Address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

* remove visitor nonsense

* remove visitor comment

Signed-off-by: Xiaodong Ye <[email protected]>

* Address review comments

Signed-off-by: Xiaodong Ye <[email protected]>

---------

Signed-off-by: Xiaodong Ye <[email protected]>
Co-authored-by: slaren <[email protected]>

…14360)

* vulkan: Handle updated FA dim2/3 definition

Pack mask boolean and n_head_log2 into a single dword to keep the push
constant block under the 128B limit.

* handle null mask for gqa

* allow gqa with dim3>1

The fused operation was grabbing the epsilon value from the wrong place.

Add an env var to disable fusion.

Add some missing checks for supported shapes/types.

Handle fused rms_norm+mul in check_results.

Commit taken from remyoudompheng's PR ggml-org#12260

Co-authored-by: Rémy Oudompheng <[email protected]>