mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-07-08 11:56:59 +00:00
Simplify llama MTP token input
This commit is contained in:
@@ -1492,7 +1492,7 @@ function _rerenderCachedModels() {
|
||||
panelHtml += `<label class="hwfit-sf-cb cookbook-llama-gpu-only"><input type="checkbox" class="hwfit-sf" data-field="vision"${sv('vision',false)?' checked':''} /> Vision${_h('Serve with the vision encoder so the model can read images. Auto-finds an mmproj-*.gguf next to the model. Adds ~1 GB VRAM.')}</label>`;
|
||||
panelHtml += `<label class="hwfit-sf-cb"><input type="checkbox" class="hwfit-sf" data-field="llama_no_mmap"${sv('llama_no_mmap',false)?' checked':''} /> No mmap${_h('Adds --no-mmap. Useful for some high-context/local-storage setups.')}</label>`;
|
||||
panelHtml += `<label class="hwfit-sf-cb"><input type="checkbox" class="hwfit-sf" data-field="llama_no_warmup"${sv('llama_no_warmup',false)?' checked':''} /> Skip warmup${_h('Adds --no-warmup. Reduces startup memory spikes; llama.cpp defaults to warming up.')}</label>`;
|
||||
panelHtml += `<label class="hwfit-sf-cb hwfit-spec-group"><input type="checkbox" class="hwfit-sf" data-field="llama_speculative_mtp"${sv('llama_speculative_mtp',false)?' checked':''} /> MTP Spec${_h('llama.cpp native MTP speculative decoding: --spec-type draft-mtp. Requires a GGUF with MTP heads.')} <span class="hwfit-numstep"><button type="button" class="hwfit-numstep-btn" data-step="-1" tabindex="-1" aria-label="Decrease">‹</button><input type="number" class="hwfit-sf hwfit-spec-tokens" data-field="llama_spec_tokens" value="${esc(sv('llama_spec_tokens', '3'))}" min="1" max="10" title="--spec-draft-n-max" /><button type="button" class="hwfit-numstep-btn" data-step="1" tabindex="-1" aria-label="Increase">›</button></span></label>`;
|
||||
panelHtml += `<label class="hwfit-sf-cb hwfit-spec-group"><input type="checkbox" class="hwfit-sf" data-field="llama_speculative_mtp"${sv('llama_speculative_mtp',false)?' checked':''} /> MTP Spec${_h('llama.cpp native MTP speculative decoding: --spec-type draft-mtp. Requires a GGUF with MTP heads.')} <input type="number" class="hwfit-sf hwfit-spec-tokens hwfit-spec-tokens-bare" data-field="llama_spec_tokens" value="${esc(sv('llama_spec_tokens', '3'))}" min="1" max="10" title="--spec-draft-n-max" /></label>`;
|
||||
panelHtml += `</div>`;
|
||||
// Row 3b: Checkboxes (diffusers)
|
||||
panelHtml += `<div class="hwfit-serve-checks hwfit-backend-diffusers">`;
|
||||
|
||||
Reference in New Issue
Block a user