Repository Issue Activity (beta)

#7548 Snippet Support on web search

#7550 Add spellcheck in the election app

#7551 Can I safely replace llama_cpp_binaries in portable app with official llama.cpp binaries if versions/backends match?

#7105 "RuntimeError: Insufficient VRAM in split for model and cache" after updating to latest version of Text Generation WebUI

#7546 Unable to load any models on my AMD RX 9070XT.

#7549 Linux electron icon

#7547 [Feature request] add API key token for Mindcraft

#7545 v4.8: UI unusable over Runpod Cloudflare proxy (slow load, broken Model tab styling)

#7544 TextGen API unable to process array of content blocks

#7542 Do not clear prompt/chat if model is not loaded.

#7541 error while handling argument "--draft-max": the argument has been removed.

#7540 Character images bug and context length reset bug on gradio share

#7468 Upgrade Web_Search to use DDGS instead of web scraping

#7536 --split-mode tensor not working for Minimax-m2

#7534 Broken text box in v4.7.3

#7535 Plain numeric line rendered as ordered-list marker

#7533 🔬 Integration Proposal: CAJAL — Local Scientific Paper Model for text-generation-webui

#7530 [ISSUE]: TextGen Fails to load GGUF models on multiple browsers, different textgen versions.

#7525 user_data/extensions not having settings saved

#7526 Add more details to extensions doc

#7519 working with images in gemma 4

#7523 New option in context menu for adding pre-defined frequently used prompts

#7517 Instruction templates loading error that didn't happen with past versions.

#7513 Thought' tags from new Gemma 4 models having very rare moments where it doesnt get hidden

#7509 Thought' tags from new Gemma 4 models are not hidden in chat.