Aperta
Eval bug: Gemma4 fails with NotImplemented: map: filter-mapping not implemented
enhancementgood first issue
9 commenti0 reazioni0 assegnatari
Issue
Aperta
Feature Request: Graceful reasoning budget termination. Avoid mid-sentence cutoff.
enhancementgood first issuehelp wanted
6 commenti0 reazioni1 assegnatario
Aperta
5 commenti0 reazioni0 assegnatari
Aperta
Misc. bug: llama-finetune won't work even with 17M parameters arch:llama
Review Complexity : Highbughelp wanted
11 commenti0 reazioni0 assegnatari
Aperta
Feature Request: support the multi-modal Bagel model
Review Complexity : Highenhancementhelp wantedmodelmtmd
1 commento1 reazione0 assegnatari
Aperta
Feature Request: support Qwen3-omni, Qwen3-TTS and MiniCPM-o
Review Complexity : Highenhancementgood first issuehelp wantedmtmdtts
13 commenti28 reazioni0 assegnatari
Aperta
Eval bug: wrong default threads in llama-bench
good first issuelow severityperformance
7 commenti0 reazioni0 assegnatari
Aperta
GGUF convert support for Vibevoice
3rd partyenhancementgood first issuehelp wantedmodeltts
3 commenti1 reazione0 assegnatari
Aperta
Eval bug: llama server response hangs for /slots/0?action=erase
bughelp wantedmedium severityserver/api
5 commenti0 reazioni0 assegnatari
Aperta
Feature Request: Implement missing ops from backends
enhancementgood first issue
33 commenti6 reazioni0 assegnatari
Aperta
tutorials : list for llama.cpp
good first issuehelp wantedroadmap
20 commenti20 reazioni0 assegnatari
Aperta
tts : add support for Orpheus
good first issuetts
7 commenti26 reazioni0 assegnatari
Aperta
Feature Request: Mapping model name to LoRA config
enhancementgood first issueserver
6 commenti2 reazioni0 assegnatari
Aperta
examples : add configuration presets
documentationenhancementexamplesgood first issuehelp wanted
9 commenti3 reazioni0 assegnatari
Aperta
Feature Request: Allow Filtering LLama Server Response Fields
enhancementgood first issue
10 commenti0 reazioni0 assegnatari
Aperta
Compile bug: ios swift xcode build error when upgrade to llama : use cmake for swift build
buildgood first issuehelp wanted
41 commenti3 reazioni0 assegnatari
Aperta
5 commenti3 reazioni0 assegnatari
Aperta
llama : add CLI assistant
enhancementgood first issueroadmap
4 commenti3 reazioni0 assegnatari
Aperta
Feature Request: llama-server hot swapping cvectors via API like we can do with LoRA adapters now
enhancementgood first issue
2 commenti4 reazioni0 assegnatari
Aperta
ggml : add ANE backend
help wantedresearch 🔬roadmap
21 commenti84 reazioni0 assegnatari