Oct 29 5 days ago 15:09 onw 3.4.0: model choice from the API, model limits in /v1/models, usage on a stream's last chunk Oct 26 8 days ago 03:17 onw 3.3.3: background compiles end with onw Oct 25 9 days ago 09:18 onw 3.3.2: UI / manager fixes, faster short MoE prompts 03:34 onw 3.3.1: fix the empty models tab with local models Oct 24 10 days ago 11:08 onw 3.3.0: LFM2.5-24B-A2B (converted on this PC), faster MoE prompts Oct 23 11 days ago 14:33 onw 3.2.2: security fix (certifi >= 2026.10.19, pip >= 26.2.2) Oct 20 14 days ago 13:02 onw 3.2.1: faster MoE answers (experts kept in their slots, bound attention for MoE, LM head compiled with profiling on), the Qwen3.6-35B-A3B NF4 build in the catalog 02:16 onw 3.2.0: Ternary Bonsai 2 4B / 9B 64-token graphs (one copy of the 2-bit weights), parallel compile in processes, faster kit compiler, paged graphs released under fused ones, vision encoder in the background Oct 19 15 days ago 09:09 onw 3.1.0: the Qwen family on fused graphs + MTP (setting, on by default), background preload of fused variants up to 4K, model list search / sort / filters 02:45 onw 3.0.0: onw NPU kit (Windows and Linux) - weightless graphs, shared weights, compiler fixes; fused graphs on by default from Lunar Lake on, up to 32K positions Oct 4 30 days ago 13:08 onw 1.3.0: Anthropic Messages API and OpenAI Responses API, thinking levels with budgets, per-model defaults, chat copy/source/regenerate 12:06 onw 1.2.3: user guide anchors fixed, Server and API screenshot, wider sampling select 11:59 onw 1.2.2: API default sampling setting (for apps that send none), chat starts from custom values 11:53 onw 1.2.1: no Gemma recompile on the 64-token switch, NPUW cache cleanup, recompile notice, no pip on every update 11:21 onw 1.2.0: llm-jp-4.1-32B-A3B-thinking (qwen3_moe) 04:53 onw 1.1.3: recommended sampling from generation_config.json / onw/sampling.json, changelog headings fixed Oct 3 22:11 onw 1.1.2: chat auto-scroll stops when scrolled up, jump-to-latest button 21:46 onw 1.1.1: Qwen3.5-9B NF4, recommended sampling in the chat 15:36 onw 1.1.0: NF4 models for Lunar Lake and newer (Ornith-1.5-9B NF4) 13:14 onw 1.0.1: user guide and new screenshots, chat formatting, Gemma repetition hint 11:26 onw 1.0.0: first stable release (settings tabs, chat fixes) 10:47 onw 0.15.3: finished downloads turn into a Load button 10:45 onw 0.15.2: model picker follows the loaded model, unsaved-settings bar 10:05 onw 0.15.1: memory-saving mode loads one block size at startup, strict memory-saving mode 08:07 onw 0.15.0: chat history, reasoning_content always + reasoning_tokens, thinking info and default, llm-jp INT8 06:10 onw 0.14.3: chat page max tokens 2048 for always-thinking models, clear message when thinking uses up the limit 05:34 onw 0.14.2: memory-saving mode for every dense model without shared weights, Gemma 4 thinking split, stale-tray warning, LM head via npuw-none first 04:10 onw 0.14.1: memory-saving mode swaps the 16-token and 1-token graphs (one set in memory at a time) 03:13 onw 0.14.0: memory-saving mode (16-token graphs only) for many-part models; no auto-reload after updates when auto-load is off 02:13 onw 0.13.2: NPUW auto-off for many-part models (Granite, llm-jp); NPU driver resource errors not recorded as route failures 02:02 onw 0.13.1: NPUW weight sharing for Qwen3.5 16-token graphs (no boolean mask constants) Oct 2 23:19 onw 0.13.0: NeoHorse-1-4B, Granite 4.2 3B / 8B, llm-jp-4.1-8b-thinking; granite / llama converter; Panther Lake listed 09:04 onw 0.12.1: load progress, download progress for updates, stale manager.json fix Oct 1 09:52 onw 0.12.0: Ornith-1.5-9B, earlier turns' reasoning_content to the template, --deltanet-fmt q8g128 Sep 29 15:53 onw 0.11.3: Ubuntu launcher no longer crashes (namespace shadowing guard, console-script launchers) 15:33 onw 0.11.2: 16 GB PCs no longer mark models as SSD-streamed 14:42 onw 0.11.1: installs again (OpenVINO pre-release index), code review fixes, gpt-oss INT8 embedding 12:32 onw 0.11.0: OpenAI gpt-oss-20b (gpt_oss: MoE, attention sinks, YaRN, harmony), INT8 code overflow fixes 09:56 onw 0.10.5: the compile cache prunes itself after a load; attention graphs in onw blob store 07:35 onw 0.10.4: keep the .bin mapped for the NPUW weights bank (crash at first inference); REP pipeline for the split parts 07:09 onw 0.10.3: NPUW works again for the split parts (Lunar Lake memory + compile time); 3720 DCOFF crash fix 05:37 onw 0.10.2: fix the experimental switches flipping back off Sep 28 23:51 onw 0.10.1: experimental NPUW settings (MoE, FUNCALL_ASYNC, weightless cache); less CPU in long chats 18:37 onw 0.10.0: long contexts with a paged INT8 KV cache (32K default, up to the model max); Gemma RoPE fix; Ubuntu launcher fix 15:07 onw 0.9.2: tool calls (function calling) in the OpenAI-compatible API 14:31 onw 0.9.1: the window closes with the tray; 'Check now' always answers; parallel update downloads 03:43 onw 0.9.0: LFM2.5 support (convert it yourself), LFM models out of the list, torch-free convert Sep 27 12:22 onw 0.8.5: after an update the onw window reopens on the new version 11:29 onw 0.8.4: English / Simplified Chinese UI, new icon, README banner 10:53 v0.8.3: update notice as a bottom-right card with progress; open windows reconnect to the restarted tray 
