Hoist the HTML-escape lookup table in static/js/ui.js out of the
String.replace callback so it is allocated once instead of on every
matched character. esc() is the canonical escaper aliased across 27
modules and runs on essentially every render, so this removes a lot of
short-lived garbage on the hottest text path. Output is byte-identical
(verified across null/undefined/emoji/attribute edge cases).
Also build the <select> option lists in cookbook-hwfit.js and group.js
by accumulating a string and assigning innerHTML once, instead of
`innerHTML +=` inside a forEach (which makes the browser re-parse the
element's markup on every iteration). Final DOM is unchanged.
Pure micro-optimizations; no behavior change.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
An image attachment only got through if the model name was on a short
built-in list. Anything else was treated as text-only and the image was
quietly dropped, so the model never saw it. That left out a lot of the
smaller vision models you can run locally (moondream was the one I hit).
Pulled the check into is_vision_model() in chat_helpers, broadened it to
cover those, and added a test. Models that already worked are unaffected.
Fixes#124.
When Cookbook installs vllm via `pip install --user vllm`, pip pulls in
nvidia-cuda-* wheels under /app/.local but doesn't set CUDA_HOME or
create /usr/local/cuda. vllm 0.22+ then crashes during engine init:
RuntimeError: Could not find nvcc and default cuda_home='/usr/local/cuda' doesn't exist
After that, the mixed cuda-nvcc 13.3 / cuda-runtime 13.0 wheel combo
fails FlashInfer's JIT sampler with:
error: "CUDA compiler and CUDA toolkit headers are incompatible"
Detect the pip-installed nvcc on startup, point CUDA_HOME at it, and
default VLLM_USE_FLASHINFER_SAMPLER=0 (sampler only, no attention
impact) so the engine boots. No-op when vllm isn't installed.
Fixes#214.
Co-authored-by: sirs <sirs@local>
pewdiepie-archdaemon