unsloth/studio/backend/core/inference
Daniel Han-Chen 4e1c622d20 Fix/adjust diffusion: gate accelerate preflight on cpu_offload for PR #5754
Backend CI on Python 3.11 failed 15 diffusion tests after R30's
accelerate preflight because the CI test environment does not
install accelerate, but the tests mock from_pretrained and never
exercise the CPU-offload path that actually needs it.

Gate the find_spec("accelerate") check on enable_model_cpu_offload
so the dependency is only required for the path that uses it.
transformers preflight stays unconditional (it is always touched
by from_pretrained). Tests with offload=False (the default) pass
without accelerate; production loads with offload=True still get
the fail-fast unload-protection guard the original round-30 fix
added.

97 targeted backend tests pass (test_diffusion_routes,
test_diffusion_backend, test_inference_model_validation,
test_data_recipe_seed, test_training_raw_support,
test_export_log_cursor).
2026-05-25 17:28:06 +00:00
..
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
_html_to_md.py fix: studio web search SSL failures and empty page content (#4754) 2026-04-01 06:12:02 -07:00
anthropic_compat.py Studio: Claude Code Anthropic API tool compatibility (#5390) 2026-05-21 16:45:05 +04:00
audio_codecs.py Add native GGUF intake to Studio (#5246) 2026-05-04 11:46:18 +02:00
chat_template_helpers.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
defaults.py studio: engage draft-mtp on vision MTP GGUFs (drop incorrect vision gate) (#5560) 2026-05-18 08:42:55 -07:00
diffusion.py Fix/adjust diffusion: gate accelerate preflight on cpu_offload for PR #5754 2026-05-25 17:28:06 +00:00
external_provider.py Studio: PDF / document attachments for Anthropic + OpenAI (#5689) 2026-05-22 06:22:57 -07:00
inference.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
key_exchange.py studio: API external provider support for chat (OpenAI, Mistral, Gemini, Cohere, Anthropic, OpenRouter, DeepSeek, custom providers) (#4706) 2026-05-14 16:13:59 +04:00
llama_cpp.py Fix/adjust diffusion: round 15 P1+P2+P3 batch for PR #5754 2026-05-25 07:00:29 +00:00
llama_server_args.py studio: add --spec-draft-n-max toggle for MTP speculative decoding (#5582) 2026-05-19 06:17:04 -07:00
mlx_inference.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
orchestrator.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
pricing.py Studio: per-session cost calculator + /api/providers/pricing endpoint (#5690) 2026-05-22 06:03:43 -07:00
providers.py Studio: expand Connections model picker for local inference server (#5643) 2026-05-20 15:06:06 +04:00
safetensors_agentic.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00
tool_call_parser.py Revert "studio: tool calling for Llama-3, Mistral, Gemma 4 on safetensors + MLX (#5615)" (#5619) 2026-05-19 07:26:39 -07:00
tools.py studio: tighten sandbox blocklist precision (bash, hf upload, NOFILE) (#5487) 2026-05-18 00:01:17 -07:00
worker.py Studio: tools, thinking blocks, code execution and web search for safetensors (#5520) 2026-05-19 06:30:17 -07:00