Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: eullm/eullm
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: EuLLM-v0.6.1-beta.4
Choose a base ref
...
head repository: eullm/eullm
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: EuLLM-v0.6.1
Choose a head ref
  • 2 commits
  • 3 files changed
  • 1 contributor

Commits on Jun 9, 2026

  1. chore(engine): 0.6.1 — multimodal vision fix (BOS) promoted to stable 

    Vision is now correct on all images (portraits, vertical/dark shots,
not just easy landscapes). Root cause was the missing <bos> token in the
shared mtmd tokenize path (fixed in 0698e2c): Gemma requires BOS, and
generate_multimodal sent the hand-built prompt without it, degrading the
model into 'wall of text / line art' confabulation on harder subjects.
Confirmed by an A/B of released binaries — beta.3 (no BOS) hallucinates,
beta.4 (BOS) sees — on both the web/API and CLI one-shot paths.

Also refresh two stale docs: the CLI --image help (the HTTP API does
route media now) and the E4B catalog blurb (the 12B gemma4uv projector
is served by the vendored llama-cpp-rs, no upstream bump pending).
    @primoco
    primoco committed Jun 9, 2026
    Configuration menu
    Copy the full SHA
    30da133 View commit details
    Browse the repository at this point in the history

  2. Merge pull request #184 from eullm/feat/web-chat-multimodal 

    chore(engine): 0.6.1 — multimodal vision fix (BOS) promoted to stable
    @primoco
    primoco authored Jun 9, 2026
    Configuration menu
    Copy the full SHA
    738aa87 View commit details
    Browse the repository at this point in the history
Loading