Skip to content

Fastembed-rs

v5.16.2 Bugfix

This release fixes issues for SREs watching stability and regressions.

Published 7d RAG & Retrieval
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

embeddings fastembed llm reranker reranking retrieval
+2 more
retrieval-augmented-generation vector-db

Summary

AI summary

Updates 🐛 Bug Fixes, 📝 Documentation, and 5.16.2 across a mixed release.

Changes in this release

Bugfix Medium

Clamp qwen3 image max_pixels to tokenizer token budget

Clamp qwen3 image max_pixels to tokenizer token budget

Source: llm_adapter@2026-06-15

Confidence: high

Bugfix Medium

Resolve dtype mismatches for BF16/F16 inference in nomic-v2-moe

Resolve dtype mismatches for BF16/F16 inference in nomic-v2-moe

Source: llm_adapter@2026-06-15

Confidence: high

Full changelog

5.16.2 (2026-06-14)

🐛 Bug Fixes

  • qwen3: clamp image max_pixels to tokenizer token budget (#260) (5340989)
  • nomic-v2-moe: resolve dtype mismatches for BF16/F16 inference (#259) (5dae66b)

📝 Documentation

  • Usage reconciliation at README.md and lib.rs docstrings (#258) (53bf4db)

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

Track Fastembed-rs

Get notified when new releases ship.

Sign up free

About Fastembed-rs

All releases →

Related context

Beta — feedback welcome: [email protected]