Skip to content

[pull] master from ggml-org:master #65

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
pull merged 4 commits into from
May 15, 2026
Merged

[pull] master from ggml-org:master #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ac33f03
reasoning-budget: clone should do a deep-copy (#23095)
am17an May 15, 2026
d5dc2e0
llama-eval : add AIME 2026 dataset support (#23058)
ggerganov May 15, 2026
769cc93
ci : fix transform of top . entry in release archive (#23080)
CISC May 15, 2026
cc7200b
Refactor: convert_hf_to_gguf.py (#17114)
pwilkin May 15, 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
16 changes: 8 additions & 8 deletions .github/workflows/release.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-macos-${{ matrix.build }}.tar.gz -s ",./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-macos-${{ matrix.build }}.tar.gz -s ",^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -182,7 +182,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-${{ matrix.build }}.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -259,7 +259,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-vulkan-${{ matrix.build }}.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -337,7 +337,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-android-arm64.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -426,7 +426,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/ReleaseOV/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ env.OPENVINO_VERSION_MAJOR }}-x64.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/ReleaseOV/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-openvino-${{ env.OPENVINO_VERSION_MAJOR }}-x64.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/ReleaseOV/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -867,7 +867,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-${{ matrix.build }}-x64.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-sycl-${{ matrix.build }}-x64.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -979,7 +979,7 @@ jobs:
id: pack_artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-ubuntu-rocm-${{ env.ROCM_VERSION_SHORT }}-${{ matrix.build }}.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down Expand Up @@ -1240,7 +1240,7 @@ jobs:
- name: Pack artifacts
run: |
cp LICENSE ./build/bin/
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-${{ matrix.chip_type }}-openEuler-${{ matrix.arch }}${{ matrix.use_acl_graph == 'on' && '-aclgraph' || '' }}.tar.gz --transform "s,./,llama-${{ steps.tag.outputs.name }}/," -C ./build/bin .
tar -czvf llama-${{ steps.tag.outputs.name }}-bin-${{ matrix.chip_type }}-openEuler-${{ matrix.arch }}${{ matrix.use_acl_graph == 'on' && '-aclgraph' || '' }}.tar.gz --transform "s,^.,llama-${{ steps.tag.outputs.name }}," -C ./build/bin .

- name: Upload artifacts
uses: actions/upload-artifact@v6
Expand Down
21 changes: 10 additions & 11 deletions common/reasoning-budget.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,22 +171,12 @@ static void common_reasoning_budget_reset(struct llama_sampler * smpl) {
ctx->force_pos = 0;
}

// forward declaration for use in clone
static struct llama_sampler * common_reasoning_budget_init_state(
const struct llama_vocab * vocab, const std::vector<llama_token> & start_tokens,
const std::vector<llama_token> & end_tokens, const std::vector<llama_token> & forced_tokens,
int32_t budget, common_reasoning_budget_state initial_state);

static struct llama_sampler * common_reasoning_budget_clone(const struct llama_sampler * smpl) {
const auto * ctx = (const common_reasoning_budget_ctx *) smpl->ctx;
return common_reasoning_budget_init_state(
ctx->vocab,
ctx->start_matcher.tokens,
ctx->end_matcher.tokens,
ctx->forced_tokens,
ctx->budget,
ctx->state);
}
static struct llama_sampler * common_reasoning_budget_clone(const struct llama_sampler * smpl);

static void common_reasoning_budget_free(struct llama_sampler * smpl) {
delete (common_reasoning_budget_ctx *) smpl->ctx;
Expand All @@ -205,6 +195,15 @@ static struct llama_sampler_i common_reasoning_budget_i = {
/* .backend_set_input = */ nullptr,
};

static struct llama_sampler * common_reasoning_budget_clone(const struct llama_sampler * smpl) {
const auto * ctx = (const common_reasoning_budget_ctx *) smpl->ctx;

return llama_sampler_init(
/* .iface = */ &common_reasoning_budget_i,
/* .ctx = */ new common_reasoning_budget_ctx(*ctx)
);
}

static struct llama_sampler * common_reasoning_budget_init_state(
const struct llama_vocab * vocab,
const std::vector<llama_token> & start_tokens,
Expand Down
Loading
Loading