ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/studio/backend/core/inference
History
Daniel Han 9a933d375b Guard old diffusers, stream video exports, record conditioned recipes 
Three fixes from review.

The 0.39-only pipeline classes (Flux2Klein, Z-Image, Krea 2, LTX-2,
HunyuanImage) were resolved by getattr deep in the load, so on the older
diffusers that packaging still allows on Python 3.9 -- diffusers dropped 3.9 in
0.38 and this project still supports it, so the 0.39 floor has to be conditional
or the extra becomes unresolvable -- an advertised model failed with a bare
AttributeError after its checkpoint had already been downloaded. Krea 2 already
guarded itself this way; assert_pipeline_class_available now runs the same check
for every image and video family from validation, before any fetch, and names
the version and the fix.

WebM export accumulated the whole VP9 output in a BytesIO and returned it as one
bytes object that the response held again. The request caps allow 2048x2048 for
1024 frames, so an export runs to hundreds of MB and concurrent clicks could
exhaust the process, while the MP4 route beside it already streamed from disk.
transcode_to_file encodes to a temp file and the route returns a FileResponse
with a background unlink, so nothing large is resident.

A conditioned generation's recipe carried only the txt2img fields, so the
gallery presented an inpaint or upscale result as a complete Create recipe and
restoring it replayed an unrelated text-to-image request. The images themselves
are still not persisted (user uploads with their own lifetime), but the workflow
and its scalars are, restore reapplies them, and the toast now names the inputs
that have to be supplied again instead of silently landing on Create.

Reported by Codex.
2026-07-27 07:41:19 +00:00
..
sandbox_site Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
__init__.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
_html_to_md.py Studio: stream live tool output with SSE heartbeats, fix web page extraction, and surface interrupted turns (#7083) 2026-07-15 08:41:00 -07:00
_vulkan_probe.py Studio: add Vulkan llama.cpp support (#5819) 2026-07-09 03:39:48 -07:00
anthropic_compat.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
api_monitor.py Studio: trim serving-log noise and surface llama-server engine stats (#6377) 2026-06-17 05:37:57 -07:00
audio_codecs.py Studio: add configurable model download location (#7274) 2026-07-23 01:34:38 -07:00
chat_eos.py Studio: stop chat generation on the assistant-turn-end token (fixes Qwen3.5 loop) (#6804) 2026-07-06 10:07:56 -07:00
chat_template_helpers.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
chat_templates.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
defaults.py Add DeepSeek-V4-Flash-GGUF to Studio with none/high/max reasoning (#6908) 2026-07-07 06:13:43 -07:00
diffusion.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
diffusion_arch_patches.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_attention.py [pre-commit.ci] auto fixes from pre-commit.com hooks 2026-07-27 07:18:14 +00:00
diffusion_auto_policy.py Fix diffusion policy and classification issues from review 2026-07-27 06:51:41 +00:00
diffusion_batched.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_cache.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_compile_cache.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_cond_cache.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_controlnet.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_device.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_eager_patches.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_engine_router.py Bound the gallery blob cache, and three interlock fixes 2026-07-27 05:08:45 +00:00
diffusion_families.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
diffusion_gguf_compile.py Tighten comments across the image generation stack 2026-07-12 10:55:39 +00:00
diffusion_hidream.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_ideogram4.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_inference_info.py Tighten comments across the image generation stack 2026-07-12 10:55:39 +00:00
diffusion_krea2.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_lora.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_memory.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_patch_backend.py Only retry the unsloth import where it can succeed 2026-07-27 07:23:29 +00:00
diffusion_precision.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_prequant.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_speed.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
diffusion_te_prequant.py [pre-commit.ci] auto fixes from pre-commit.com hooks 2026-07-27 04:29:44 +00:00
diffusion_transformer_quant.py Fix diffusion policy and classification issues from review 2026-07-27 06:51:41 +00:00
external_provider.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
gpu_arbiter.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
image_gallery.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
inference.py Add Intel XPU support to Unsloth Studio (#4724) 2026-07-24 02:22:07 -03:00
key_exchange.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
llama_admission.py Studio: queue local GGUF OpenAI-compatible requests before llama-server (#7047) 2026-07-10 17:05:48 -03:00
llama_cpp.py Merge branch 'main' of https://github.com/unslothai/unsloth into r6763 2026-07-27 07:15:43 +00:00
llama_http.py fix(studio/llama_cpp): disable trust_env on the loopback health probe (#6750) (#6752) 2026-06-30 19:09:26 +02:00
llama_keepwarm.py Merge origin/main into image-generation (PR #6763) 2026-07-25 00:34:38 -07:00
llama_server_args.py persist llama.cpp KV cache across idle auto-unload (slot save/restore) (#7204) 2026-07-20 00:12:42 -07:00
llama_stats.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
local_model_resolver.py Add interactive Agents command builder (#7312) 2026-07-26 17:09:19 -07:00
mcp_client.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
mcp_config_import.py studio: show MCP "Import config" on the add-server form (#6030) 2026-06-11 16:17:22 +01:00
message_content.py fix(studio): handle multimodal list content in inference text paths (#4383) (#6480) 2026-06-23 01:26:11 -07:00
mlx_inference.py Studio: reuse MLX prompt cache across turns instead of re-prefilling (#7311) 2026-07-22 02:35:33 -07:00
model_ids.py studio: list the full local model catalog from /v1/models (#6519) 2026-06-26 20:42:06 -03:00
orchestrator.py Add Intel XPU support to Unsloth Studio (#4724) 2026-07-24 02:22:07 -03:00
passthrough_healing.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
presence_penalty.py Studio: apply presence_penalty on the safetensors and MLX inference paths (#6923) 2026-07-06 22:24:47 -07:00
pricing.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
providers.py Allow API key for Ollama connections (#7173) 2026-07-18 22:47:00 -07:00
runtime_context.py Expose runtime context length for hub models (#6154) 2026-06-11 22:13:53 +03:00
safetensors_agentic.py Studio: default tool-call permission to Approve for me, prompt only on high-risk actions (#7285) 2026-07-26 17:07:31 -07:00
sd_cpp_args.py Keep the sd.cpp text encoder on CPU under Metal 2026-07-27 06:58:36 +00:00
sd_cpp_backend.py Bound the gallery blob cache, and three interlock fixes 2026-07-27 05:08:45 +00:00
sd_cpp_engine.py Bound the gallery blob cache, and three interlock fixes 2026-07-27 05:08:45 +00:00
sd_cpp_server.py Bound the gallery blob cache, and three interlock fixes 2026-07-27 05:08:45 +00:00
stt_ggml_sidecar.py Studio: add local speech-to-text dictation engine (#7095) 2026-07-23 01:39:03 -07:00
stt_sidecar.py Studio STT: only load safetensors weights for custom dictation models (RCE fix) (#7364) 2026-07-23 03:15:45 -07:00
tensor_fallback.py studio: deterministic VRAM auto-fit for GGUF (MTP reserve, compute buffer, total-based budget) (#6312) 2026-06-17 03:10:22 -07:00
tool_call_parser.py Studio: Inkling support fixes (#7153) 2026-07-15 11:22:38 -07:00
tool_loop_controller.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
tool_stream_exec.py Studio: stream live tool output with SSE heartbeats, fix web page extraction, and surface interrupted turns (#7083) 2026-07-15 08:41:00 -07:00
tools.py Studio: add Deep Research (#7219) 2026-07-26 23:36:02 -07:00
video.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
video_families.py Trim the comments across the diffusion backend 2026-07-26 20:31:19 +00:00
video_gallery.py Guard old diffusers, stream video exports, record conditioned recipes 2026-07-27 07:41:19 +00:00
video_ltx2.py Stop staging the dense text encoder for an fp8 video load 2026-07-27 04:28:12 +00:00
web_access_policy.py Studio: add Deep Research (#7219) 2026-07-26 23:36:02 -07:00
worker.py Add Intel XPU support to Unsloth Studio (#4724) 2026-07-24 02:22:07 -03:00