LocalAI v4.5.6

v4.5.6
Added 4
  • SyncedMap component for distributed cross-replica state
  • LOCALAI_DISTRIBUTED_SHARED_MODELS environment variable to skip staging on shared volumes
  • Voice-detect and face-detect ggml backends to replace Python insightface/speaker-recognition
  • Semantic VAD EOU token for realtime
Changed 1
  • Migrate finetune/quant/agent-tasks to cross-replica state
Fixed 14
  • Missing agent NATS permission in distributed mode
  • Fall back to DefaultContextSize for unparseable GGUFs and pin NVFP4 gallery context_size
  • Gallery mmproj/model quant matching to prevent F16 from selecting BF16
  • Return empty backend list for agent nodes instead of failing backend.list
  • Bound resume-stream buffer and enforce response ownership in openresponses
  • IK-llama multimodal path ported to mtmd API
Removed 1
  • Drop the darwin/metal build target for fish-speech

From LocalAI

What's Changed
👒 Dependencies
Other Changes
New Contributors

Full Changelog: https://github.com/mudler/LocalAI/compare/v4.5.5...v4.5.6

View original

Upgraded? How did it go?

Discussion