Add Qwen2.5-VL-3B-Instruct model knowledge (vlm + verified perf)#89
Open
rjckkkkk wants to merge 1 commit into
Open
Add Qwen2.5-VL-3B-Instruct model knowledge (vlm + verified perf)#89rjckkkkk wants to merge 1 commit into
rjckkkkk wants to merge 1 commit into
Conversation
… perf) Without a catalog entry the scanned GGUF (Qwen2.5-VL-3B-Instruct-Q4_K_M) was auto-detected with no type, so `openclaw sync` skipped it (default case) and the model never surfaced as an OpenClaw provider. Add the model yaml: type vlm, metadata.aliases for the scan name, openclaw.chat_provider so it surfaces as a multimodal (text+image) chat provider, a universal llamacpp gguf variant, and verified perf (AMD Strix Halo / llama.cpp b9330: ~90 tok/s text decode; vision verified with --mmproj). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
rjckkkkk
added a commit
that referenced
this pull request
Jun 12, 2026
) New version-stamped build aima-windows-amd64-v0.5-dev-amd-strix-halo-20260612.exe (source commit fa35aa4) on top of the HIP-engine build. Adds, vs the 20260610 exe: #87 native deploy readiness uses the real runtime name (no false "not ready") #88 deploy launcher hidden (no cmd.exe console popup) via VBS launcher #89 Qwen2.5-VL-3B-Instruct catalog knowledge (vlm + aliases + verified perf) #90 zero-config vision: llama.cpp --mmproj auto-wired for VL gguf models #91 openclaw sync preflight-probes :6188 and warns loudly when unreachable serve.bat now points at the 20260612 exe; older builds kept for rollback. README build table + fixes list + OpenClaw data-plane guidance updated. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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.
What
Catalog model yaml for Qwen2.5-VL-3B-Instruct (
type: vlm,aliases: [Qwen2.5-VL-3B-Instruct-Q4_K_M],openclaw.chat_provider: true, a universal llamacpp gguf variant, verified Strix Halo perf).Why
Without a catalog entry the scanned GGUF was auto-detected with no type, so
aima openclaw synchit itsdefault(skip) branch → the deployed model never became an OpenClaw provider (sync reportedvlm=0). With the yaml, the model has a type → sync writes it as anaimaprovider and sets it as the default chat model.Verified (AMD Strix Halo Win11 rig, llama.cpp b9330)
Deployed → text decode ~90 tok/s; vision verified (started with
--mmproj, correctly identified a test image). After this yaml,aima openclaw sync→providers=aima, modelqwen2.5-vl-3b-instruct,chatModel=aima/qwen2.5-vl-3b-instruct.Note: image input requires llama-server's
--mmproj(pass--config mmproj=<path>); auto-wiring the projector is a separate enhancement.🤖 Generated with Claude Code