oobabooga 4737744f4a Security: Fix SSRF vulnerabilities in URL fetching

2026-04-22 14:43:16 -07:00

..

api

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

grammar

Add missing __init__.py to modules/grammar

2026-03-20 16:04:57 -03:00

callbacks.py

Minor cleanup

2026-03-20 07:20:26 -07:00

chat.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

evaluate.py

Make user_data configurable: add --user-data-dir flag, auto-detect ../user_data

2026-03-05 19:31:10 -08:00

exllamav3_hf.py

Reduce VRAM peak in prompt logprobs forward pass

2026-04-10 19:21:57 -07:00

exllamav3.py

Fix bos/eos tokens not being set for models without a chat template

2026-04-12 16:01:00 -07:00

extensions.py

Several small code simplifications

2026-03-30 19:36:03 -07:00

html_generator.py

Add tool call confirmation with inline approve/reject buttons

2026-04-22 11:49:39 -07:00

image_models.py

Fix image generation: default to SDPA attention backend

2026-04-05 20:03:06 -07:00

image_utils.py

Security: Fix SSRF vulnerabilities in URL fetching

2026-04-22 14:43:16 -07:00

llama_cpp_server.py

llama.cpp: Pass --draft-min 48 by default for draftless speculative decoding

2026-04-22 13:00:48 -07:00

loaders.py

UI: Only show reasoning effort/enable thinking for models that use them

2026-04-18 13:45:35 -07:00

logging_colors.py

Rename project from text-generation-webui to textgen

2026-04-13 17:03:19 -03:00

logits.py

Logits display improvements (#7486)

2026-04-14 22:29:19 -03:00

LoRA.py

Remove ExLlamaV2 backend

2026-03-05 14:02:13 -08:00

metadata_gguf.py

fix: replace bare except clauses with except Exception (#7400)

2026-03-04 18:06:17 -03:00

models_settings.py

Fix bos/eos tokens being overwritten after GGUF metadata sets them (closes #7496)

2026-04-15 13:14:27 -07:00

models.py

Rename "truncation length" to "context length" in logs

2026-03-25 07:21:02 -07:00

paths.py

Portable mode: always use ../user_data if it exists

2026-03-06 18:04:48 -08:00

presets.py

Move top_p and top_k higher up in the UI and CLI help

2026-03-15 09:34:17 -07:00

prompts.py

fix(security): sanitize filenames in all prompt file operations (CWE-22) (#7462)

2026-04-03 19:36:50 -03:00

reasoning.py

Fix GPT-OSS tag leak during streaming between thinking and tool calls

2026-04-06 12:06:28 -07:00

sampler_hijack.py

Add adaptive-p sampler and n-gram speculative decoding support

2026-03-04 09:41:29 -08:00

sane_markdown_lists.py

Disable uncommonly used indented codeblocks (#7401)

2026-03-04 17:51:00 -03:00

shared.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

tensorrt_llm.py

TensorRT-LLM: Migrate from ModelRunner to LLM API, add concurrent API request support

2026-03-05 18:09:45 -08:00

text_generation.py

UI: Add an error message when no model is loaded

2026-04-14 21:05:56 -07:00

tool_parsing.py

Lint

2026-04-14 20:28:55 -07:00

tool_use.py

Add tool call confirmation with inline approve/reject buttons

2026-04-22 11:49:39 -07:00

torch_utils.py

Remove obsolete DeepSpeed inference code (2023 relic)

2026-03-04 17:20:34 -08:00

training.py

Rename project from text-generation-webui to textgen

2026-04-13 17:03:19 -03:00

transformers_loader.py

Don't pass torch_dtype to transformers, autodetect from model config

2026-04-02 00:44:14 -03:00

ui_chat.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

ui_default.py

fix(security): sanitize filenames in all prompt file operations (CWE-22) (#7462)

2026-04-03 19:36:50 -03:00

ui_file_saving.py

Use logger.exception() instead of traceback.print_exc() for error messages

2026-03-18 20:42:20 -07:00

ui_image_generation.py

Image generation: Embed generation metadata in API image responses

2026-04-04 23:15:14 -07:00

ui_model_menu.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

ui_notebook.py

fix(security): sanitize filenames in all prompt file operations (CWE-22) (#7462)

2026-04-03 19:36:50 -03:00

ui_parameters.py

Move top_p and top_k higher up in the UI and CLI help

2026-03-15 09:34:17 -07:00

ui_session.py

API: Move OpenAI-compatible API from extensions/openai to modules/api

2026-03-20 14:46:00 -03:00

ui.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

utils.py

Add preserve_thinking chat template parameter (UI and CLI)

2026-04-22 13:43:56 -07:00

web_search.py

Security: Fix SSRF vulnerabilities in URL fetching

2026-04-22 14:43:16 -07:00