onw / onw

947 kB

Ctrl+K

1 contributor

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

1e8e4dd verified 1 day ago

models
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 1 day ago
web
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 1 day ago
__init__.py

221 Bytes
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 1 day ago
__main__.py

4.36 kB
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 6 days ago
app.py

54 kB
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 1 day ago
cachever.py

2.33 kB
onw 1.4.1: Panther Lake (NPU 5) runs - fix DEVICE_LOST at the first inference; fix compiling again at every load on Windows (read-only cache files); ~3x faster first compile on Panther Lake 7 days ago
chat.py

50.9 kB
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 1 day ago
compact.py

8.89 kB
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 6 days ago
compat.py

25.5 kB
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 6 days ago
convert.py

5.22 kB
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 1 day ago
deps.py

5.43 kB
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 6 days ago
dl.py

1.31 kB
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 6 days ago
hub.py

2.15 kB
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 6 days ago
i18n.json

61.1 kB
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 1 day ago
i18n.py

2.86 kB
onw 0.8.4: English / Simplified Chinese UI, new icon, README banner 15 days ago
ir.py

26.6 kB
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 1 day ago
kvcache.py

14.9 kB
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 6 days ago
logo.py

4.55 kB
onw 0.8.4: English / Simplified Chinese UI, new icon, README banner 15 days ago
manager.py

34 kB
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 1 day ago
paged.py

16.8 kB
onw 0.11.0: OpenAI gpt-oss-20b (gpt_oss: MoE, attention sinks, YaRN, harmony), INT8 code overflow fixes 13 days ago
parts.py

980 Bytes
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 10 days ago
precompile.py

768 Bytes
onw 1.4.1: Panther Lake (NPU 5) runs - fix DEVICE_LOST at the first inference; fix compiling again at every load on Windows (read-only cache files); ~3x faster first compile on Panther Lake 7 days ago
probe.py

3.05 kB
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 6 days ago
prune.py

9.62 kB
onw 0.3: --context at load time, top_k / penalties, tray app + setup scripts, --compact / --prune 18 days ago
relaunch.py

2.97 kB
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 6 days ago
runtime.py

118 kB
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 1 day ago
sampling.json

1.49 kB
onw 1.2.0: llm-jp-4.1-32B-A3B-thinking (qwen3_moe) 8 days ago
server.py

35.8 kB
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 6 days ago
store.py

12.7 kB
onw 0.11.1: installs again (OpenVINO pre-release index), code review fixes, gpt-oss INT8 embedding 13 days ago
tools.py

6.05 kB
onw 0.11.1: installs again (OpenVINO pre-release index), code review fixes, gpt-oss INT8 embedding 13 days ago
tray.py

15.2 kB
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 6 days ago
uninstall.py

5.96 kB
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 6 days ago
update.py

6.4 kB
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 6 days ago
usage.py

6.44 kB
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 6 days ago
winshell.py

5.29 kB
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 6 days ago
xio.py

5.52 kB
onw 0.11.1: installs again (OpenVINO pre-release index), code review fixes, gpt-oss INT8 embedding 13 days ago