sync: engine 0.1.6 — Qwen 3.5/3.6 support, headers, binding mirrors#18
Merged
Conversation
…+ bindings - base-convert: Qwen 3.5/3.6 hybrid arch (config extraction, GDN tensor precision rules, MoE MTP/fused-expert handling, mrope recording), catalog updates, CLI banner, version 0.1.6 - headers: new config fields + baseRT_set_verbose / baseRT_model_config_sizeof - bindings (python/rust/node/swift): BaseRTModelConfig mirrors updated to the current 1520-byte layout + load-time size guards Requires the 0.1.6 engine binaries: the size guard rejects older libbaseRT builds.
Same casing fix as #15 applied to ci.yml: the Fetch engine step matched nothing since the rebrand, so the engine-linked ABI tests were silently skipped. With the pattern fixed the rust-sys ABI check runs against the latest engine release — it will fail on this PR until the 0.1.6 engine is published, which enforces the intended merge ordering.
Contributor
Author
|
Note: also fixed the |
The initial sync was taken from the release branch before it merged; the tag additionally carries llama3 rope_scaling config fields (struct is 1540 bytes) and the converter's llama rope fixes. Mirrors verified against the published v0.1.6 engine binaries.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Sync with engine 0.1.6.
BaseRTModelConfigfields;baseRT_set_verbose(),baseRT_model_config_sizeof().Merge with (or after) the v0.1.6 engine release — the bindings' size guard rejects older
libbaseRTbuilds. Tested: converter suite green; python/rust bindings verified against a 0.1.6 engine build (size cross-check passes).