Skip to content

Releases: lloyal-ai/lloyal.node

v1.1.0

04 Feb 16:49

Choose a tag to compare

Full Changelog: v1.0.9...v1.1.0

v1.0.9

04 Feb 16:48

Choose a tag to compare

Full Changelog: v1.0.8...v1.0.9

v1.0.8

02 Feb 07:26

Choose a tag to compare

Synced with upstream: liblloyal and llama.cpp

Full Changelog: v1.0.7...v1.0.8

v1.0.7

01 Feb 01:52

Choose a tag to compare

lloyal.node v1.0.7 — First Stable Release

The first stable release of @lloyal-labs/lloyal.node. Ships the Branch API for covalent generation and prebuilt binaries across 13 platform/GPU combinations.

Branch API

New Branch class for forkable inference. Each branch owns a KV cache sequence, sampler chain, logits snapshot, and perplexity tracker. Under unified KV, forking is a metadata-only operation — no KV tensor buffers are copied.

Key methods:

  • Branch.create() / fork() — create root or fork from any branch (root or intermediate) to build trees
  • produce() / commit() — two-phase protocol: sample without KV write, then commit to advance
  • prune() — discard loser branch and its divergent KV entries
  • destroy() — release handle but keep KV (for winners continuing with raw ops)
  • reseedSampler() — unique PRNG per fork for stochastic diversity
  • perplexity — rolling PPL per branch for quality-based selection

Updated Examples

  • best-of-n — Rewritten with Branch API. Parallel streaming generation with perplexity selection.
  • speculative — Rewritten with Branch API. Draft/verify with fork and prune.
  • streaming-summary — New. Infinite context generation via BlinkKV reseeding with sidecar summarization model and ghostwritten progress sinks.

Other Changes

  • liblloyal upgraded to v1.0.4 (Branch API, DEFAULT_N_BATCH fix, slot reuse leak fix)\
  • Removed vestigial APIs from public surface

Platforms

Prebuilt binaries for macOS (arm64 Metal, x64), Linux (x64/arm64 × CPU/CUDA/Vulkan), Windows (x64 × CPU/CUDA/Vulkan, arm64 × CPU/Vulkan).