LM-Kit.NET 릴리스

Released: Jun 22, 2026

2026.6.4 버젼 업데이트

기능

  • Made context hibernation improvements.
  • Improved inference speed.
  • Added KV Cache quantization support. Introduced new property 'Configuration.EnableKVCacheQuantization'.

Released: Jun 15, 2026

2026.6.3 버젼 업데이트

기능

  • Improved inference speed.
  • Improved overall extraction accuracy.

Released: Jun 9, 2026

2026.6.2 버젼 업데이트

기능

  • Improved inference speed with structured content extraction with MTP and draft models.

Released: Jun 8, 2026

2026.6.1 버젼 업데이트

기능

  • Added a model card for gemma4:12b: Google Gemma 4 11.9B dense model with 256K context, hybrid sliding/global attention, vision, tool calling, math, coding, and reasoning support. gemma4:12b is now the replacement model for the deprecated gemma3:12b.
  • Added draft model support. Introduced a new 'LM.DraftModel' property.
  • Improved inference speed.

Released: May 31, 2026

2026.5.6 버젼 업데이트

기능

  • Added model card for paddleocr-vl-1.6:0.9b: PaddleOCR-VL 1.6, an ultra-compact 0.9B vision-language model for document parsing (OCR, tables, formulas, charts, text spotting, seals, layout analysis), reaching 96.33% on OmniDocBench v1.6 (state of the art). Architecturally compatible with 1.5 for drop-in migration. The paddleocr-vl:0.9b model card is now deprecated in favor of paddleocr-vl-1.6:0.9b.
  • Added PostgreSQL pgvector integration (LM-Kit.NET.Data.Connectors.PgVector): a new...

Released: May 28, 2026

2026.5.5 버젼 업데이트

기능

  • Context hibernation policy (HibernationMode, IKVCache, Configuration, MultiTurnConversation, PdfChat, RagChat, AgentExecutor): new HibernationMode enum (Auto, None, Forced), per-conversation IKVCache.HibernationMode get/set property on every multi-turn conversation type, and a process-wide Configuration.DefaultContextHibernationMode that seeds the value on every new conversation. In Forced mode the runtime hibernates the KV-cache to disk in the background at the end of every turn...

Released: May 24, 2026

2026.5.4 버젼 업데이트

기능

  • Stream-based model loading (LMKit.Model): new LM(Stream) loads GGUF and LMK archives from a stream; LM.LoadEncryptedFromStream(...) does the same for encrypted GGUF (.lmke). No on-disk extraction.
  • Markdown attachment support (LMKit.Data.Attachment, LM-Kit.Server): .md / .markdown files are now recognized as plain-text attachments (text/markdown), handled identically to .txt end to end.
  • Multi-Token Prediction (MTP) self-speculative decoding: a new generation accelerator for models...

Released: May 18, 2026

2026.5.3 버젼 업데이트

기능

  • Added Windows ARM64 platform support: LM-Kit.NET now ships native binaries for Windows ARM64 alongside the existing Windows x64, Linux x64, Linux ARM64, and macOS Universal targets. Covers Snapdragon X / Copilot+ PCs, Surface Pro X / Surface Pro 9 (5G), Windows Dev Kit 2023, and other Qualcomm-powered Windows 11 devices. The base LM-Kit.NET package now contains a runtimes/win-arm64/native/ folder with the default CPU (ARM Neon) and Vulkan backends (Qualcomm Adreno acceleration via Vulkan...

Released: May 10, 2026

2026.5.2 버젼 업데이트

기능

  • Added model cards for Qwen 3.6 family: qwen3.6:27b (27B dense hybrid Gated DeltaNet + Gated Attention model, 64 blocks) and qwen3.6:35b-a3b (35B MoE, 3B active, 256 experts with 8 routed plus 1 shared, 40 blocks). Both support chat, vision, tool calling, code completion, math, and OCR with a native 262K context window extensible to 1M tokens via YaRN. The qwen3.5:27b and qwen3.5:35b-a3b model cards are now deprecated in favor of qwen3.6:27b and qwen3.6:35b-a3b respectively.
  • Added...

Released: May 6, 2026

2026.5.1 버젼 업데이트

기능

  • Extended encrypted GGUF support to metadata-only scenarios (LMKit.Cryptography, LMKit.Model, LMKit.Hardware): LM.LoadEncrypted now honors LoadingOptions.LoadTensors = false, mirroring the plaintext metadata-only path - only the metadata block is decrypted, no tensor bytes are read, and the resulting LM exposes architecture, vocabulary, context length, layer count, and other GGUF metadata. Use this for fast catalog inspection or pre-flight checks on protected .lmke containers.
  • Added...