ci(release): ship llama-speculative-simple in prebuilt archives#69
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
Enables llama-speculative-simple in Prism prebuilt release archives.
Changes:
- Enables example targets across shared release builds.
- Existing catch-all packaging includes generated binaries.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| env: | ||
| BRANCH_NAME: ${{ github.head_ref || github.ref_name }} | ||
| CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON" | ||
| CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=ON -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON" |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The prebuilt release archives ship
llama-server,llama-cli, and the tools, but notllama-speculative-simple(the dspark / speculative-decoding CLI), because the release build sets-DLLAMA_BUILD_EXAMPLES=OFFand that binary lives underexamples/.llama-serveralready includes speculative support, so the API path works from prebuilds; only the CLI one-shot is missing.This flips the shared
CMAKE_ARGSto-DLLAMA_BUILD_EXAMPLES=ONso the binary is built and picked up by the existingtar -C build/bin ./7zpackaging on every platform (macOS, Linux, CUDA, Vulkan, Windows). No packaging change needed.Trade-off:
EXAMPLES=ONalso builds the otherexamples/*binaries, so the archives grow by that set (this matches upstream's default). If you'd rather ship onlyllama-speculative-simple, keepEXAMPLES=OFFand add a targetedcmake --build build --target llama-speculative-simplestep before packaging instead; happy to switch to that if you prefer the slimmer archives.