Skip to content

9596; fix M5 performance; check for llama #107

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
conda-forge-admin merged 2 commits into from
Jun 11, 2026
Merged

9596; fix M5 performance; check for llama #107

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
4d4788e
9596; fix M5 performance; check for llama
xhochy Jun 11, 2026
f4c964e
Build more releases
xhochy Jun 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
2 changes: 1 addition & 1 deletion .ci_support/osx_64_.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
MACOSX_DEPLOYMENT_TARGET:
- '11.0'
MACOSX_SDK_VERSION:
- '11.0'
- '26.1'
blas_impl:
- accelerate
c_compiler:
Expand Down
2 changes: 1 addition & 1 deletion .ci_support/osx_arm64_.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
MACOSX_DEPLOYMENT_TARGET:
- '11.0'
MACOSX_SDK_VERSION:
- '11.0'
- '26.1'
blas_impl:
- accelerate
c_compiler:
Expand Down
2 changes: 1 addition & 1 deletion conda-forge.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ azure:
bot:
automerge: true
version_updates:
random_fraction_to_keep: 0.02
random_fraction_to_keep: 0.2
conda_build:
error_overlinking: true
conda_build_tool: rattler-build
Expand Down
6 changes: 4 additions & 2 deletions recipe/conda_build_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,7 @@
c_stdlib_version: # [osx and x86_64]
- '11.0' # [osx and x86_64]
c_stdlib_version: # [osx]
- '11.0' # [osx]
MACOSX_SDK_VERSION: # [osx]
- '26.1' # [osx]

blas_impl:
- mkl # [(linux and not aarch64) or win]
Expand Down
5 changes: 3 additions & 2 deletions recipe/recipe.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
context:
name: llama.cpp
version: "9574"
version: "9596"
build: 0
# ensure arm_variant_type gets detected as a used variable
touch_arm_variant_type: ${{ arm_variant_type if (linux and aarch64) else "None" }}
Expand All @@ -11,7 +11,7 @@ package:

source:
url: https://github.com/ggml-org/${{ name }}/archive/b${{ version ~ "" | split(".") | list | last }}.tar.gz
sha256: a482a5d45e291aff8eca06ee3c902f7f4af665a451feeac6dcbb504ab365b420
sha256: c80caadf88a211c6d6e7820ded7258a6c2c0a476926a04dd7e8708ba3e552c93

build:
# See https://conda-forge.org/docs/user/tipsandtricks/#installing-cuda-enabled-packages-like-tensorflow-and-pytorch
Expand Down Expand Up @@ -228,6 +228,7 @@ tests:

# Check binaries
- echo "Checking binary files..."
- check_file "$PREFIX/bin/llama" "llama"
- check_file "$PREFIX/bin/llama-batched" "llama-batched"
- check_file "$PREFIX/bin/llama-batched-bench" "llama-batched-bench"
- check_file "$PREFIX/bin/llama-bench" "llama-bench"
Expand Down