Repository navigation
feat(gallery): add Spark-X2.6 4B variants - #12821
Closed
localai-org-maint-bot wants to merge 4 commits into
Closed
localai-org-maint-bot wants to merge 4 commits into
localai-org-maint-bot wants to merge 4 commits into
Conversation
localai-org-maint-bot
force-pushed
the
gallery/20261022-second-pass
branch
from
October 23, 2026 08:08
c7be61f to
23c59fa
Compare
Add the publisher Q4_K_M and Q8_0 builds with pinned downloads and verified SHA256 hashes. Document installation and variant selection. Assisted-by: Codex:gpt-6
Implement InstallLibraryBackend so the assistant tests satisfy the LocalAIClient interface after the library integration. Assisted-by: Codex:GPT-6
localai-org-maint-bot
force-pushed
the
gallery/20261022-second-pass
branch
from
October 23, 2026 10:07
23c59fa to
2e55645
Compare
Merge current master and remove the redundant InstallLibraryBackend stub that prevents the MCP endpoint tests from compiling. Assisted-by: Codex:gpt-6
Collaborator
|
Landed on master in 8b0d6c0 (batched gallery update). |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Add Spark-X2.6-4B Q4_K_M and Q8_0 GGUF builds as linked llama.cpp variants, with installation examples. Both use the embedded chat template, publisher sampling defaults, and a 32,768-token default context.
Source: XHToken's model card and weights.
Notes for Reviewers
7f7b10fba.fe31f8d64890302cc3a1d365d700357b4b75ba77. Each SHA256 matches both Hugging Face LFS metadata and the pinned download URL'sx-linked-etagheader.spark2_5and contain a Jinja chat template. LocalAI's pinned llama.cpp commit includessrc/models/spark2-5.cpp; this is the architecture used by existing Spark-X2.5 entries.go test ./core/gallery -count=1 -ginkgo.focus='gallery/index.yaml|gallery variant lint',go test ./scripts/build/gallery -count=1,go run ./scripts/build/gallery . gallery <output>, andgit diff --check.go test ./core/gallery -count=1: 494 passed, 3 failed, 9 skipped. The three failures involve external GitHub fixtures returning Forbidden. No inference test was run.Signed commits