• Stefy Lanza (nextime / spora )'s avatar
    front: route gguf bare alias by capability to its real engine, not nvidia · 482e47cf
    Stefy Lanza (nextime / spora ) authored
    pick_engine honours the front's assignment (radeon) only if the engine
    can_serve the request's required capability. But _required_cap derived
    that capability from the bare alias 'coe-…-q4_k_m' — no literal 'gguf' —
    so required_capability returned 'transformers' (CUDA-only). radeon is
    gguf-only, failed can_serve, and the request fell through to the default
    engine (nvidia), even though compute_assignment had correctly placed the
    model on radeon (it sees the full '…-q4_k_m.gguf' path).
    
    Resolve the model's configured path in _load_pins (now indexed by the
    .gguf-stripped stem too) and, when the name heuristic yields
    'transformers' but that path is a .gguf, correct the capability to
    'gguf'. whisper/ds4 precedence is unchanged. Combined with the registry
    stem-matching, a bare-alias request now lands on the owning Vulkan/AMD
    engine.
    Co-Authored-By: 's avatarClaude Opus 4.8 <noreply@anthropic.com>
    482e47cf
Name
Last commit
Last update
..
admin Loading commit data...
api Loading commit data...
backends Loading commit data...
broker Loading commit data...
frontproxy Loading commit data...
models Loading commit data...
openai Loading commit data...
pydantic Loading commit data...
queue Loading commit data...
tasks Loading commit data...
__init__.py Loading commit data...
cli.py Loading commit data...
config.py Loading commit data...
main.py Loading commit data...
platform_paths.py Loading commit data...