Daniel Han eeffa4c065 studio: web search, KV cache dtype, training progress, inference fixes ... ## Summary - Add web search tool calling for GGUF models (Search toggle, DuckDuckGo via ddgs) - Add KV cache dtype dropdown (f16/bf16/q8_0/q5_1/q4_1) in Chat Settings - Fix Qwen3/3.5 inference defaults per official docs (thinking on/off params) - Enable reasoning by default for Qwen3.5 4B and 9B - Replace "Generating" toast with inline spinner - Fix stop button via asyncio.to_thread (event loop no longer blocked) - Fix CUDA 12 compat lib paths for llama-server on CUDA 13 systems - Fix auto-load model name not appearing in selector - Training progress messages + dataset_num_proc fix Integrated PRs: - #4327 (imagineer99): BETA badge alignment (already in tree) - #4340 (Manan Shah): prioritize training models in model selection - #4344 (Roland Tannous): setup.sh macOS python version compatibility - #4345 (Manan Shah): revamp model+dataset checking logic		2026-03-17 00:30:01 -07:00
..
__init__.py	Update license headers	2026-03-12 17:23:10 +00:00
chat_templates.py	studio: web search, KV cache dtype, training progress, inference fixes	2026-03-17 00:30:01 -07:00
data_collators.py	Final cleanup	2026-03-12 18:28:04 +00:00
dataset_utils.py	studio: web search, KV cache dtype, training progress, inference fixes	2026-03-17 00:30:01 -07:00
format_conversion.py	Final cleanup	2026-03-12 18:28:04 +00:00
format_detection.py	Final cleanup	2026-03-12 18:28:04 +00:00
llm_assist.py	Improve AI Assist: Update default model, model output parsing, logging, and dataset mapping UX (#4323)	2026-03-16 16:04:35 +04:00
model_mappings.py	Final cleanup	2026-03-12 18:28:04 +00:00
vlm_processing.py	Final cleanup	2026-03-12 18:28:04 +00:00