* build: fix the cache keys for Windows HIP release job
Update the cache keys to include the HIP SDK version, preventing the
use of outdated ROCm installation caches.
* build: sync changes from release.yml to build.yml
- Update HIP SDK version to 25.Q3 and ROCm version to 6.4.2
- Update the cache keys to reflect the new versions
* build: remove Windows HIP release for gfx1151
since the current stable rocWMMA does not support gfx1151.
Use this to query register count for shader compiles on NVIDIA. Currently
this is only for performance debug, but it could eventually be used in some
heuristics like split_k.
* metal : refactor bin kernels loading
ggml-ci
* metal : refactor rms kernel loading
ggml-ci
* ci : try to add memory leaks check
ggml-ci
* ci : try to enable memory leak detection for Mac
* cont : seems to be working
To pull and run models via: llama-server -dr gemma3
Add some validators and sanitizers for Docker Model urls and metadata
Signed-off-by: Eric Curtin <eric.curtin@docker.com>
* ggml-backend : add GGML_BACKEND_DEVICE_TYPE_IGPU device type
ggml-backend : add device id to device props
llama : only use iGPU devices if there are no GPU devices
llama : do not use multiple devices from different backends with the same device id
This commit adds a check for GGML_MACHINE_SUPPORTS_i8mm when enabling
MATMUL_INT8 features, ensuring that i8mm intrinsics are only used when
the target hardware actually supports them.
The motivation for this is to fix ggml CI build failures where the
feature detection correctly identifies that i8mm is not supported,
adding the +noi8mm flag, but MATMUL_INT8 preprocessor definitions are
still enabled, causing the compiler to attempt to use vmmlaq_s32
intrinsics without i8mm support.
Refs: https://github.com/ggml-org/ggml/actions/runs/17525174120/job/49909199499
Since the prefill length is not fixed, graphs constructed for the
prefill stage cannot be reused. For this reason, ACL graph
execution is disabled by default during prefill.
* Add fastdiv and fastmodulo to k_bin_bcast kernel
* Address review comments
* `prod_` instead of `prod` suffix
* Add test case for `k_bin_bcast_unravel` in CUDA backend
* support non-contiguous Q in build_attn_mha
* Update src/llama-graph.cpp
ggml-ci
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit fixes the zero padding for odd dimensions in
ggml_compute_forward_timestep_embedding_f32.
The motivation for this is that currently if an odd dimension is used,
the padding check incorrectly uses the dimension value for indexing.
For example, with dim=15:
Elements 0-6 are set to cosine values
Elements 7-13 are set to sine values
Element 14 is left uninitialized (contains garbage)
Element 15 is correctly set to zero
This fix changes embed_data[dim] to embed_data[2 * half] so that
element 14 (the first unused element) is properly set to zero as well
as the last element.
Resolves: https://github.com/ggml-org/ggml/issues/1324
* metal : make the backend async
ggml-ci
* cont : add comments, extend op offload, clean up
ggml-ci
* metal : fix batch size for MUL_MAT_ID
* metal : remove deprecated ggml_backend_metal_buffer_from_ptr
* metal : create only metal buffers, no wrapping of host memory
ggml-ci
* metal : restore .alloc_buffer for buffer_from_ptr_type
ggml-ci
* metal : remove broken implementation of GGML_OP_SET
ggml-ci
* metal : clean-up loose ends, ready for tests
ggml-ci
* metal : support both private and shared buffers
ggml-ci
* metal : enable private buffers + add global device queue
* metal : disable host buffer to prevent races
ggml-ci
* metal : avoid extra copy during set_tensor
ggml-ci
* metal : use separate buffer types for shread and private Metal buffers
ggml-ci
* metal : simplify synchronization logic
ggml-ci
* metal : fix build
ggml-ci
* metal : do not implement cpy_tensor
ggml-ci
* metal : separate implementations for shared and private buffers
ggml-ci
This commit applies the same caching to the release workflow which
currently exists for the main CI workflow that was introduced in Commit
ff02caf9ee ("ci : cache ROCm installation
in windows-latest-cmake-hip (#15887)").
* CANN: Add ROPE sin/cos cache for reuse
Introduce sin/cos caching mechanism in ROPE to avoid redundant
computation across layers. The cache is built on the first layer
per device and reused by subsequent layers if parameters match.
- Added sin_cache / cos_cache pointers and position_length tracking
- Introduced cache validity flags and properties:
(ext_factor, theta_scale, freq_scale, attn_factor, is_neox)
- Accelerates ROPE by eliminating repeated sin/cos generation
This change reduces overhead in multi-layer scenarios while
preserving correctness by verifying parameter consistency.
Co-authored-by: hipudding <huafengchun@gmail.com>
* fix typo
Signed-off-by: noemotiovon <757486878@qq.com>
---------
Signed-off-by: noemotiovon <757486878@qq.com>
Co-authored-by: hipudding <huafengchun@gmail.com>
* CANN: implement LRU cache for ACL graphs in CANN backend
- Introduce ggml_cann_graph_lru_cache to store multiple ggml_cann_graph objects.
- Graphs are loaded on demand and evicted using LRU policy when capacity is exceeded.
- Updated push, move_to_front, and clear methods to manage cached graphs efficiently.
- Ensures reuse of graphs, reducing graph reconstruction overhead in CANN backend.
* fix typo
* The LRU cache capacity can be configured via an env variable
Signed-off-by: noemotiovon <757486878@qq.com>
* refactory acl graph
* refactory && fix review comments
Signed-off-by: noemotiovon <757486878@qq.com>
---------
Signed-off-by: noemotiovon <757486878@qq.com>
This commit adds check for two function pointers returned from
ggml_backend_reg_get_proc_address.
The motivation for this is that the function pointer could be nullptr if
the get proc address function changes in the future. This is also
consistent with all the other calls to ggml_backend_reg_get_proc_address
in the code base.
This commit adds caching of the ROCm installation for the windows-latest-cmake-hip job.
The motivation for this is that the installation can sometimes hang and/or not complete properly leaving an invalid installation which later fails the build. By caching the installation hopefully we can keep a good installation available in the cache and avoid the installation step.
Refs: https://github.com/ggml-org/llama.cpp/pull/15365
* CUDA: Add mul_mat_id support the mmf
Add support for mul_mat_id for bs < 16
* Review: use warp_size, fix should_use_mmf condition
* Launch one block per expert, stride along n_expert_used
* templatize mul_mat_id
* Pad shmem to 16 bytes, add helper function mul_mat_f_switch_ids
* Reduce compile times by dividing mmf into f16, bf16 and f32 variants
* Divide mmf by ncols_dst
* Add missing files
* Fix MUSA/HIP builds
* requirements : update transformers/torch for Embedding Gemma
This commit updates the requirements to support converting
Embedding Gemma 300m models.
The motivation for this change is that during development I had a local
copy of the transformers package which is what I used for converting
the models. This was a mistake on my part and I should have also updated
my transformers version to the official release.
I had checked the requirements/requirements-convert_legacy_llama.txt
file and noted that the version was >=4.45.1,<5.0.0 and came to the
conculusion that no updated would be needed, this assumed that
Embedding Gemma would be in a transformers release at the time
Commit fb15d649ed ("llama : add support
for EmbeddingGemma 300m (#15798)) was merged. So anyone wanting to
convert themselves would be able to do so. However, Embedding Gemma is
a preview release and this commit updates the requirements to use this
preview release.
* resolve additional python dependencies
* fix pyright errors in tokenizer test and remove unused import
* feat: Extra debugging support for model conversion - added BF16 support for llama-callback-eval and support for dumping intermediate steps in run-org-model.py
* vulkan: sort graph to allow more parallel execution
Add a backend proc to allow the backend to modify the graph. The
vulkan implementation looks at which nodes depend on each other
and greedily reorders them to group together nodes that don't
depend on each other. It only reorders the nodes, doesn't change
the contents of any of them.
With #15489, this reduces the number of synchronizations needed.
* call optimize_graph per-split
