Add MTP speculative decoding support#1027
Open
DINOZYAVIER wants to merge 9 commits into
Open
Conversation
Newer llama.cpp builds publish libllama-common and libllama-common-base instead of libcommon. Detect the produced common archives before emitting cargo link directives so full release builds can resolve the MTP wrapper dependencies.
2ade832 to
be3eb5b
Compare
Contributor
|
the crate version is already correct - otherwise the changes are welcome. I'll merge once version fixed and CI is clean. |
Author
|
It looks like the workflow may have been cancelled due to a timeout. Before pushing, I built both targets that did not finish in CI: linux/amd64 completed fairly quickly, while arm64 took more than an hour. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Rust bindings for llama.cpp MTP speculative decoding.
Changes
ac7680n_rs_seq, context type)MtpSpeculativesafe wrapperVerification
cargo fmt --checkgit diff --check origin/main..HEADcargo test -p llama-cpp-2