Add --webui arg to launch llama.cpp new webui#786

Merged

ikawrakow merged 38 commits intomainfrom

fcp/alt_frontend

Oct 27, 2025

Commits on Oct 26, 2025

Add new webui from llama.cpp
firecoperana
committed
Add new webui
firecoperana
committed
feat: Improve mobile UI for Settings Dialog (#16084)

allozaur
authored and
firecoperana
committed
webui : fix handling incomplete chunks (#16107)

Bramas
authored and
firecoperana
committed
Always show message actions for mobile UI + improvements for user message sizing (#16076)

allozaur
authored and
firecoperana
committed
webui: switch to hash-based routing (alternative of #16079) (#16157)

isaac-mcfadyen
authored and
firecoperana
committed
Allow viewing conversations even when llama server is down (#16255)

authored and
firecoperana
committed
Enhance text file detection logic for file attachments (#16199)

allozaur
authored and
firecoperana
committed
Show message actions by default (#16289)

allozaur
authored and
firecoperana
committed
fix: preserved zero values in chat settings inputs and textareas by switching to nullish coalescing for field values and default placeholders (#16312)

ServeurpersoCom
authored and
firecoperana
committed
Improve Mobile UI for dialogs and action dropdowns (#16222)

authored and
firecoperana
committed
Fix thinking blocks with quotes + add handling `[THINK]...[/THINK]` blocks (#16326)

authored and
firecoperana
committed
Chatapi ignore empty sampling (#16330)

ServeurpersoCom
authored and
firecoperana
committed
webui: Remove running `llama-server` within WebUI `dev.sh` script (#16363)

allozaur
authored and
firecoperana
committed
Add optional setting for showing "Model used:" information (#16337)

allozaur
authored and
firecoperana
committed
Improve code block color theming (#16325)

allozaur
authored and
firecoperana
committed
Conversation action dialogs as singletons from Chat Sidebar + apply conditional rendering for Actions Dropdown for Chat Conversation Items (#16369)

allozaur
authored and
firecoperana
committed
fix: track viewportHeight via window.innerHeight to avoid unwanted scrolling (#16356)

authored and
firecoperana
committed
webui : Fix messages payload sent to chat completions (#16402)

allozaur
authored and
firecoperana
committed
Capture model name only after first token (streaming) or completed request (#16405)

allozaur
authored and
firecoperana
committed
Fix missing messages on sibling navigation (#16408)

allozaur
authored and
firecoperana
committed
webui : added download action (#13552) (#16282)

authored and
firecoperana
committed
refactor: centralize CoT parsing in backend for streaming mode (#16394)

authored and
firecoperana
committed
No markdown in cot (#16483)

ServeurpersoCom
authored and
firecoperana
committed
webui: updated the chat service to only include max_tokens in the req… (#16489)

ServeurpersoCom
authored and
firecoperana
committed
feat: render user content as markdown option (#16358)

ServeurpersoCom
authored and
firecoperana
committed
webui: remove client-side context pre-check and rely on backend for limits (#16506)

authored and
firecoperana
committed
fix: add remark plugin to render raw HTML as literal text (#16505)

ServeurpersoCom
authored and
firecoperana
committed
Add server-driven parameter defaults and syncing (#16515)

allozaur
authored and
firecoperana
committed
fix: added a normalization step for MathJax-style \[\] and \(\) delimiters (#16599)

ServeurpersoCom
authored and
firecoperana
committed
webui: reorganize settings layout (#16607)

ServeurpersoCom
authored and
firecoperana
committed
Enable per-conversation loading states to allow having parallel conversations (#16327)

allozaur
authored and
firecoperana
committed
Import/Export UX improvements (#16619)

authored and
firecoperana
committed
Prevent premature submission on IME input (#16673)

allozaur
authored and
firecoperana
committed
Handle legacy 'context' attachments (#16687)

allozaur
authored and
firecoperana
committed
webui: introduce OpenAI-compatible model selector in JSON payload (#16562)

authored and
firecoperana
committed
webui: support q URL parameter (#16728)

authored and
firecoperana
committed
build fix
firecoperana
committed