Hugging Face's logo

ryugyosoft
/
onw

OpenVINO
Japanese
English
npu
intel
intel-npu
Mixture of Experts
inference-engine
Model card Files
xet
 Community
onw / MANUAL.md

Commit History

6 days ago

  1. onw 3.5.0: benchmark page (prefill + decode at 128-8K tokens) instead of the check page; prefill / decode speed in the chat header

    ryugyosoft
    Verified signature
    aff4893

7 days ago

  1. onw 3.4.0: model choice from the API, model limits in /v1/models, usage on a stream's last chunk

    ryugyosoft
    Verified signature
    29d8491

12 days ago

  1. onw 3.3.0: LFM2.5-24B-A2B (converted on this PC), faster MoE prompts

    ryugyosoft
    Verified signature
    7ed2518

19 days ago

  1. onw 2.0.2: dense 64-token prompt blocks on all NPUs again - NPUW_DQ_FULL=NO on NPU 5000+ (the cause of the Panther Lake errors); Panther Lake Qwen3.5-9B 44 -> ~157 tok/s

    ryugyosoft
    Verified signature
    fe7bfc4

20 days ago

  1. onw 2.0.1: dense 64-token prompt blocks only on the NPU 3720 (they gave wrong output on Panther Lake NPU 5010); NPU 4000+ back to the 1.4 block sizes

    ryugyosoft
    Verified signature
    026a99a

  2. onw 2.0.0: Qwen3.6 MoE prompts ~4-6x (grouped experts), dense prompts ~2-2.5x (64-token blocks), faster MoE decode

    ryugyosoft
    Verified signature
    aee23d2

25 days ago

  1. onw 1.4.9: Ternary Bonsai 2 27B (2-bit weights on NPU 4000+, Hadamard in-graph, onw convert reads Prism ML MLX packs); chat max tokens default to the context; settings marked that recompile; driver/OpenVINO update notice

    ryugyosoft
    Verified signature
    1e8e4dd

29 days ago

  1. onw 1.4.8: review fixes across the window, tray, chat, API and engine; uninstall; pip after the restart; memory bar and NPU load; read-only weight mappings on Windows

    ryugyosoft
    Verified signature
    e4f1d27

30 days ago

  1. onw 1.4.2: fix loading on Windows Lunar Lake (no memory-mapped blob import), parallel first compile on every NPU (off in the memory-saving mode), fix recompiling at every load on Panther Lake, merged compile-route records

    ryugyosoft
    Verified signature
    db1779c

  1. onw 1.4.0: MTP draft tokens (~1.5x answers on Lunar Lake, NF4 Qwen3.5 family), 64-token prompt blocks on Lunar Lake, less host work per step, fix all-zero logit rows

    ryugyosoft
    Verified signature
    eff87bb

  1. onw 1.3.0: Anthropic Messages API and OpenAI Responses API, thinking levels with budgets, per-model defaults, chat copy/source/regenerate

    ryugyosoft
    Verified signature
    ca9925f

  2. onw 1.2.3: user guide anchors fixed, Server and API screenshot, wider sampling select

    ryugyosoft
    Verified signature
    c2b6596

  3. onw 1.2.2: API default sampling setting (for apps that send none), chat starts from custom values

    ryugyosoft
    Verified signature
    0d57fed

  4. onw 1.1.3: recommended sampling from generation_config.json / onw/sampling.json, changelog headings fixed

    ryugyosoft
    Verified signature
    5f280a9

  1. onw 1.1.2: chat auto-scroll stops when scrolled up, jump-to-latest button

    ryugyosoft
    Verified signature
    9ccf79f

  2. onw 1.1.1: Qwen3.5-9B NF4, recommended sampling in the chat

    ryugyosoft
    Verified signature
    ac21b16

  3. onw 1.0.1: user guide and new screenshots, chat formatting, Gemma repetition hint

    ryugyosoft
    Verified signature
    88f5b6e