Skip to content

feat: update llama.cpp to e3a74b299 #2310

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

Merged
abetlen merged 1 commit into from
Jun 16, 2026
+15 −3
Merged

feat: update llama.cpp to e3a74b299 #2310

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

## [Unreleased]

- feat: update llama.cpp to ggml-org/llama.cpp@6eab47181
- feat: update llama.cpp to ggml-org/llama.cpp@e3a74b299

## [0.3.29]

Expand Down
14 changes: 13 additions & 1 deletion llama_cpp/mtmd_cpp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,6 +169,12 @@ class mtmd_caps(Structure):
POINTER(c_char_p),
)

mtmd_helper_post_decode_callback = CFUNCTYPE(
c_int,
llama_cpp.llama_batch,
c_void_p,
)


class mtmd_helper_bitmap_wrapper(Structure):
"""Bitmap wrapper returned by MTMD helper media loaders."""
Expand Down Expand Up @@ -860,7 +866,9 @@ def mtmd_helper_eval_chunk_single(
# llama_pos n_past,
# llama_seq_id seq_id,
# int32_t n_batch,
# llama_pos * new_n_past);
# llama_pos * new_n_past,
# mtmd_helper_post_decode_callback callback,
# void * user_data);
@ctypes_function(
"mtmd_helper_decode_image_chunk",
[
Expand All @@ -872,6 +880,8 @@ def mtmd_helper_eval_chunk_single(
llama_cpp.llama_seq_id,
c_int,
POINTER(llama_cpp.llama_pos),
mtmd_helper_post_decode_callback,
c_void_p,
],
c_int,
)
Expand All @@ -884,6 +894,8 @@ def mtmd_helper_decode_image_chunk(
seq_id: llama_cpp.llama_seq_id,
n_batch: Union[c_int, int],
new_n_past: "_Pointer[llama_cpp.llama_pos]",
callback: Optional[mtmd_helper_post_decode_callback],
user_data: c_void_p,
/,
) -> int:
"""Decode a pre-encoded image chunk."""
Expand Down
2 changes: 1 addition & 1 deletion vendor/llama.cpp
Open in desktop
Submodule llama.cpp updated 35 files
+3 −2 .devops/intel.Dockerfile
+1 −1 README.md
+6 −2 common/chat-auto-parser-generator.cpp
+1 −0 common/chat-auto-parser.h
+8 −0 common/chat-diff-analyzer.cpp
+17 −8 common/chat-peg-parser.cpp
+4 −2 common/chat-peg-parser.h
+3 −2 common/chat.cpp
+22 −2 common/peg-parser.cpp
+12 −10 docs/backend/SYCL.md
+30 −2 docs/install.md
+4 −4 docs/ops.md
+37 −35 docs/ops/SYCL.csv
+7 −0 ggml/src/ggml-sycl/binbcast.cpp
+21 −1 ggml/src/ggml-sycl/concat.cpp
+133 −1 ggml/src/ggml-sycl/dmmv.cpp
+25 −51 ggml/src/ggml-sycl/element_wise.cpp
+2 −0 ggml/src/ggml-sycl/element_wise.hpp
+205 −14 ggml/src/ggml-sycl/ggml-sycl.cpp
+115 −0 ggml/src/ggml-sycl/mmvq.cpp
+17 −0 ggml/src/ggml-sycl/mmvq.hpp
+98 −12 ggml/src/ggml-vulkan/ggml-vulkan.cpp
+61 −0 ggml/src/ggml-vulkan/vulkan-shaders/col2im_1d.comp
+7 −3 ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+1 −1 tests/peg-parser/test-gbnf-generation.cpp
+3 −3 tests/test-backend-ops.cpp
+75 −2 tests/test-chat.cpp
+7 −0 tools/llama-bench/llama-bench.cpp
+18 −3 tools/mtmd/mtmd-helper.cpp
+5 −1 tools/mtmd/mtmd-helper.h
+8 −9 tools/mtmd/mtmd.cpp
+3 −0 tools/server/bench/bench.py
+0 −31 tools/server/server-common.cpp
+0 −9 tools/server/server-common.h
+27 −77 tools/server/server-context.cpp
Loading