Daniel Han 465aef844c MLX diffusion backend: decode the sysctl chip name as UTF-8 (#13430) ... #13379 added a subprocess.run(text=True) with no encoding in _chip_name, which test_text_io_encoding flags on main (it would fall back to the locale codec under a C/POSIX locale). Pass encoding='utf-8', errors='replace' like the other inference subprocess calls, and apply the formatter hook to the file.		2026-10-12 07:08:15 -07:00
..
backend	MLX diffusion backend: decode the sysctl chip name as UTF-8 (#13430)	2026-10-12 07:08:15 -07:00
frontend	Studio: let models use the browser panel (#13372)	2026-10-12 06:42:40 -07:00
scripts
src-tauri	Studio: let models use the browser panel (#13372)	2026-10-12 06:42:40 -07:00
systemd
.npmrc
__init__.py
audio_cpp_prebuilt_pins.json
INFERENCE_ENGINES.md	Studio: install and run vLLM on AMD GPUs, on Linux and through WSL on Windows (#12785)	2026-10-11 03:13:49 -07:00
install_audio_cpp_prebuilt.py	Studio: install the Vulkan audio.cpp build on AMD GPUs (#13298)	2026-10-11 17:05:35 -07:00
install_lemonade_prebuilt.py	Studio: show the installed Lemonade and FastFlowLM versions on the NPU (#13151)	2026-10-10 04:14:02 -07:00
install_llama_prebuilt.py	Studio: use the Vulkan llama.cpp bundle, not CPU, on Windows NVIDIA drivers below CUDA 12.4 (#13129)	2026-10-09 06:39:55 -07:00
install_manifest.py
install_mxc_prebuilt.py
install_node_prebuilt.py
install_python_stack.py	Studio setup: install causal-conv1d and mamba-ssm prebuilt wheels next to flash-attn (#13396)	2026-10-12 06:23:20 -07:00
install_q4nx_converter.py
install_sd_cpp_prebuilt.py	Studio: pin sd.cpp to the mirror build with Windows CUDA, sharing llama.cpp's CUDA runtime (#13175)	2026-10-12 10:43:51 -03:00
install_whisper_prebuilt.py
lemonade_prebuilt_pins.json	Studio: pin FastFlowLM 1.0.7 for Qwen3.8 27B on the AMD NPU and keep Lemonade / FastFlowLM current (#13047)	2026-10-08 07:57:33 -07:00
LICENSE.AGPL-3.0
MCP.md
node_prebuilt_pins.json
nvidia_probe.py
NVLINK_P2P.md
package-lock.json
package.json
PDF_OCR.md
prebuilt_core.py	Studio: keep CUDA 12 llama.cpp prebuilts off drivers older than CUDA 12.4 (#13031)	2026-10-08 09:54:21 -07:00
q4nx_converter_pins.json
ROCM_RDNA2_APU.md
setup.bat
setup.ps1	Studio: torch 2.13 for new Windows x64 cu130 Python 3.13 installs, existing installs keep their torch (#13263)	2026-10-11 05:27:01 -07:00
setup.sh	install.sh: install XPU PyTorch on Linux when an Intel Arc / Data Center GPU is the only GPU (#13193)	2026-10-10 05:02:22 -07:00
SKILL_MENTIONS.md	Studio: let @skill mentions work without Code and add bulk skill toggles (#13163)	2026-10-10 21:26:46 +13:00
Unsloth_Studio_Colab.ipynb