This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryFixed --codebook trellis support for Gemma-4 E2B/E4B models at quantize and load time.
Full changelog
Patch release. One fix since v0.7.1:
--codebook trellis now works on Gemma-4 E2B/E4B (models with per-layer-input embeddings). The PLE embedding table routes to the shell codebook on BOTH sides — at quantize time (the trellis codebook forbids padded RHT, so PLE previously hit an assert) and at load time (E8RHTEmbedding only has a shell decode path, so trellis-quantized checkpoints previously failed with an attribute error).
Validated end-to-end on gemma-4-E2B and gemma-4-E2B-it at trellis-3INST 4 bpw: quantization completes, the checkpoint loads through the official AutoModelForMultimodalLM path, and sampled generation is coherent.
No kernel or format changes — checkpoints produced by 0.7.0/0.7.1 load unchanged.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Glq
All releases →Beta — feedback welcome: [email protected]