Skip to content

feat: update ggml to 0.16.0 #183

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
abetlen wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

feat: update ggml to 0.16.0 #183

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cd8a3e2
feat: update ggml to 0.16.0
abetlen Jul 11, 2026
3b21620
docs: add ggml 0.16.0 changelog entry
abetlen Jul 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

- feat: update ggml to 0.16.0 by @abetlen in #183
- feat: add buffer protocol support to utils by @aisk in #175

## [0.0.45]
Expand Down
28 changes: 9 additions & 19 deletions ggml/ggml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,9 +307,9 @@ def f_(*args: Any, **kwargs: Any):
GGML_EXIT_ABORTED = 1

GGML_VERSION_MAJOR = 0
GGML_VERSION_MINOR = 15
GGML_VERSION_PATCH = 3
GGML_VERSION = "0.15.3"
GGML_VERSION_MINOR = 16
GGML_VERSION_PATCH = 0
GGML_VERSION = "0.16.0"

GGML_ROPE_TYPE_NORMAL = 0
GGML_ROPE_TYPE_NEOX = 2
Expand Down Expand Up @@ -483,7 +483,8 @@ def ggml_fp32_to_bf16_row(fp32: CtypesPointer[ctypes.c_float], bf16: CtypesPoint
# GGML_TYPE_MXFP4 = 39,
# GGML_TYPE_NVFP4 = 40,
# GGML_TYPE_Q1_0 = 41,
# GGML_TYPE_COUNT = 42,
# GGML_TYPE_Q2_0 = 42,
# GGML_TYPE_COUNT = 43,
# };
GGML_TYPE_F32 = 0
GGML_TYPE_F16 = 1
Expand Down Expand Up @@ -519,7 +520,8 @@ def ggml_fp32_to_bf16_row(fp32: CtypesPointer[ctypes.c_float], bf16: CtypesPoint
GGML_TYPE_MXFP4 = 39
GGML_TYPE_NVFP4 = 40
GGML_TYPE_Q1_0 = 41
GGML_TYPE_COUNT = 42
GGML_TYPE_Q2_0 = 42
GGML_TYPE_COUNT = 43


# // precision
Expand Down Expand Up @@ -576,6 +578,7 @@ def ggml_fp32_to_bf16_row(fp32: CtypesPointer[ctypes.c_float], bf16: CtypesPoint
# GGML_FTYPE_MOSTLY_MXFP4 = 25, // except 1d tensors
# GGML_FTYPE_MOSTLY_NVFP4 = 26, // except 1d tensors
# GGML_FTYPE_MOSTLY_Q1_0 = 27, // except 1d tensors
# GGML_FTYPE_MOSTLY_Q2_0 = 28, // except 1d tensors
# };
GGML_FTYPE_UNKNOWN = -1
GGML_FTYPE_ALL_F32 = 0
Expand Down Expand Up @@ -604,6 +607,7 @@ def ggml_fp32_to_bf16_row(fp32: CtypesPointer[ctypes.c_float], bf16: CtypesPoint
GGML_FTYPE_MOSTLY_MXFP4 = 25
GGML_FTYPE_MOSTLY_NVFP4 = 26
GGML_FTYPE_MOSTLY_Q1_0 = 27
GGML_FTYPE_MOSTLY_Q2_0 = 28


# // available tensor operations:
Expand Down Expand Up @@ -15783,20 +15787,6 @@ def ggml_backend_cuda_allreduce_tensor(
...


# GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(int main_device, const float * tensor_split);
@ggml_function(
"ggml_backend_cuda_split_buffer_type",
[ctypes.c_int, ctypes.POINTER(ctypes.c_float)],
ggml_backend_buffer_type_t_ctypes,
enabled=GGML_USE_CUDA,
)
def ggml_backend_cuda_split_buffer_type(
main_device: Union[ctypes.c_int, int],
tensor_split: CtypesArray[ctypes.c_float],
) -> Optional[ggml_backend_buffer_type_t]:
...


# // pinned host buffer for use with the CPU backend for faster copies between CPU and GPU
# GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_cuda_host_buffer_type(void);
@ggml_function(
Expand Down
2 changes: 1 addition & 1 deletion vendor/ggml
Open in desktop
Submodule ggml updated 141 files
Loading