What’s New

LocalAI v4.5.6

v4.5.6
Added
  • 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
  • Migrate finetune/quant/agent-tasks to cross-replica state
Fixed
  • 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
  • Kokoro add explicit click dependency so spacy CLI works on intel build
  • Launcher binary download/upgrade with resume, rate-limit, and improved UX
  • Fish-speech allow invalid_reference_casting so tokenizers builds on darwin
  • OCI retry layer downloads on transient network errors
  • SGLang parse tool_call function arguments before applying the chat template
  • OpenAI stop max_tokens streaming retry loop on reasoning models
  • Import derive model name from selected GGUF for repo-root URIs
  • Avoid quadratic-time debug logging in CleanupLLMResult and ParseFunctionCall
Removed
  • Drop the darwin/metal build target for fish-speech
What's Changed
👒 Dependencies
Other Changes
New Contributors

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

View original