..
grammar
Handle both int and str types in grammar char processing
2025-07-23 11:52:51 -07:00
callbacks.py
Refactor the transformers loader ( #6859 )
2025-04-20 13:33:47 -03:00
chat.py
Replace PyPDF2 with pymupdf for PDF text extraction
2026-03-04 06:43:37 -08:00
deepspeed_parameters.py
Fix typo in deepspeed_parameters.py ( #3222 )
2023-07-24 11:17:28 -03:00
evaluate.py
Revert "Safer usage of mkdir across the project"
2025-06-17 07:11:59 -07:00
exllamav2.py
Lint
2025-08-12 13:37:37 -07:00
exllamav2_hf.py
Make exllamav3_hf and exllamav2_hf functional again
2025-09-17 12:29:22 -07:00
exllamav3.py
exllamav3: Implement the logits function for /v1/internal/logits
2025-10-09 11:24:25 -07:00
exllamav3_hf.py
Lint
2025-10-15 13:15:01 -07:00
extensions.py
Better log message when extension requirements are not found
2025-07-06 17:44:41 -07:00
html_generator.py
Refactor thinking block detection and add Solar Open support
2026-01-28 08:21:34 -08:00
image_models.py
Image: Quantize the text encoder for lower VRAM
2025-12-05 13:08:46 -08:00
image_utils.py
Image generation: Safer image uploading
2025-12-03 16:07:51 -08:00
llama_cpp_server.py
Delegate GPU layer allocation to llama.cpp's --fit
2026-03-04 06:37:50 -08:00
loaders.py
Add slider for --ubatch-size for llama.cpp loader, change defaults for better MoE performance ( #7316 )
2025-11-21 16:56:02 -03:00
logging_colors.py
Lint
2023-12-19 21:36:57 -08:00
logits.py
exllamav3: Implement the logits function for /v1/internal/logits
2025-10-09 11:24:25 -07:00
LoRA.py
Refactor the transformers loader ( #6859 )
2025-04-20 13:33:47 -03:00
metadata_gguf.py
llama.cpp: read instruction template from GGUF metadata ( #4975 )
2023-12-18 01:51:58 -03:00
models.py
exllamav3: Implement the logits function for /v1/internal/logits
2025-10-09 11:24:25 -07:00
models_settings.py
Delegate GPU layer allocation to llama.cpp's --fit
2026-03-04 06:37:50 -08:00
presets.py
More UI persistence: presets and characters ( #7051 )
2025-06-08 01:58:02 -03:00
prompts.py
Fix the UI failing to launch if the Notebook prompt is too long
2025-08-30 08:42:26 -07:00
sampler_hijack.py
Fix the exllamav2_HF and exllamav3_HF loaders
2025-04-21 18:32:23 -07:00
sane_markdown_lists.py
Sane handling of markdown lists ( #6626 )
2025-01-04 15:41:31 -03:00
shared.py
Delegate GPU layer allocation to llama.cpp's --fit
2026-03-04 06:37:50 -08:00
tensorrt_llm.py
Lint
2025-05-15 21:19:19 -07:00
text_generation.py
Remove a comment
2025-08-11 12:33:38 -07:00
torch_utils.py
Add fallbacks after 93aa7b3ed3
2025-10-09 10:59:34 -07:00
training.py
fix: Rename 'evaluation_strategy' to 'eval_strategy' in training
2025-10-28 16:48:04 -03:00
transformers_loader.py
Make --trust-remote-code immutable from the UI/API
2025-10-14 20:47:01 -07:00
ui.py
feat: Add a dropdown to save/load user personas ( #7367 )
2026-01-14 20:35:08 -03:00
ui_chat.py
Use a new gr.Headless component for efficient chat streaming
2026-03-03 18:12:03 -08:00
ui_default.py
Fix the UI failing to launch if the Notebook prompt is too long
2025-08-30 08:42:26 -07:00
ui_file_saving.py
feat: Add a dropdown to save/load user personas ( #7367 )
2026-01-14 20:35:08 -03:00
ui_image_generation.py
Revert "Clear the torch cache between sequential image generations"
2025-12-07 12:23:19 -08:00
ui_model_menu.py
Delegate GPU layer allocation to llama.cpp's --fit
2026-03-04 06:37:50 -08:00
ui_notebook.py
Fix the UI failing to launch if the Notebook prompt is too long
2025-08-30 08:42:26 -07:00
ui_parameters.py
Ignore add_bos_token in instruct prompts, let the jinja2 template decide
2025-07-10 07:14:01 -07:00
ui_session.py
Rename a button in the Session tab for clarity
2025-07-07 11:28:47 -07:00
utils.py
feat: Add a dropdown to save/load user personas ( #7367 )
2026-01-14 20:35:08 -03:00
web_search.py
Fix web search (attempt)
2025-08-14 12:05:14 -07:00
f010aa1612