fix index out of range on zero layer metal load ()

If the model doesn't fit any layers on metal, and we load zero layers
we would panic trying to look up the GPU size during scheduling ops
This commit is contained in:
Daniel Hiltgen 2024-11-18 11:48:13 -08:00 committed by GitHub
parent a14f76491d
commit 81d55d3e4d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -1092,7 +1092,9 @@ func (s *llmServer) EstimatedTotal() uint64 {
func (s *llmServer) EstimatedVRAMByGPU(gpuID string) uint64 {
for i, gpu := range s.gpus {
if gpu.ID == gpuID {
return s.estimate.GPUSizes[i]
if i < len(s.estimate.GPUSizes) {
return s.estimate.GPUSizes[i]
}
}
}
return 0