Binary wheels #1247
Merged
Binary wheels #1247
Conversation
This file contains 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
|
I have been building llama-cpp-python wheels for each new release in my fork of jllllll's repository: https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/actions It has some minor changes to avoid hitting rate limit errors. It also builds for all Mac versions (I think jllllll removed Mac 11 due to an error that used to happen but doesn't anymore). |
|
@oobabooga yes I saw, really appreciate you guys carrying that! I'll probably port over those release workflows and modify them so they name the release based on the version and backend tag ie It would be great if we can reduce the number of builds per release though. |
|
Any chance intel arc binaries could also be added? Thanks |
With Intel's new IPEX-LLM release this is no longer necessary. A pointer to this however might be useful as it isn't well advertised. |
xhedit
pushed a commit
to xhedit/llama-cpp-conv
that referenced
this pull request
Apr 6, 2024
* Generate binary wheel index on release * Add total release downloads badge * Update download label * Use official cibuildwheel action * Add workflows to build CUDA and Metal wheels * Update generate index workflow * Update workflow name
xhedit
added a commit
to xhedit/llama-cpp-conv
that referenced
this pull request
Apr 6, 2024
* feat: add support for KV cache quantization options (abetlen#1307) * add KV cache quantization options abetlen#1220 abetlen#1305 * Add ggml_type * Use ggml_type instead of string for quantization * Add server support --------- Co-authored-by: Andrei Betlen <[email protected]> * fix: Changed local API doc references to hosted (abetlen#1317) * chore: Bump version * fix: last tokens passing to sample_repetition_penalties function (abetlen#1295) Co-authored-by: ymikhaylov <[email protected]> Co-authored-by: Andrei <[email protected]> * feat: Update llama.cpp * fix: segfault when logits_all=False. Closes abetlen#1319 * feat: Binary wheels for CPU, CUDA (12.1 - 12.3), Metal (abetlen#1247) * Generate binary wheel index on release * Add total release downloads badge * Update download label * Use official cibuildwheel action * Add workflows to build CUDA and Metal wheels * Update generate index workflow * Update workflow name * feat: Update llama.cpp * chore: Bump version * fix(ci): use correct script name * docs: LLAMA_CUBLAS -> LLAMA_CUDA * docs: Add docs explaining how to install pre-built wheels. * docs: Rename cuBLAS section to CUDA * fix(docs): incorrect tool_choice example (abetlen#1330) * feat: Update llama.cpp * fix: missing logprobs in response, incorrect response type for functionary, minor type issues. Closes abetlen#1328 abetlen#1314 * fix: missing logprobs in response, incorrect response type for functionary, minor type issues. Closes abetlen#1328 Closes abetlen#1314 * feat: Update llama.cpp * fix: Always embed metal library. Closes abetlen#1332 * feat: Update llama.cpp * chore: Bump version --------- Co-authored-by: Limour <[email protected]> Co-authored-by: Andrei Betlen <[email protected]> Co-authored-by: lawfordp2017 <[email protected]> Co-authored-by: Yuri Mikhailov <[email protected]> Co-authored-by: ymikhaylov <[email protected]> Co-authored-by: Sigbjørn Skjæret <[email protected]>
xhedit
pushed a commit
to xhedit/llama-cpp-conv
that referenced
this pull request
Apr 30, 2024
* Generate binary wheel index on release * Add total release downloads badge * Update download label * Use official cibuildwheel action * Add workflows to build CUDA and Metal wheels * Update generate index workflow * Update workflow name
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.
Adds initial support for releasing binary wheels. Uses github-pages to publish one index per backend (CPU, Metal, CUDA, etc) to a static site.
Planned release tags for this PR (because I can test these):
cpucu121cu122cu123metalUsage (won't work until merge)
CPU
Metal
CUDA (12.1)
TODO
Related: #1178, #243 and #741