fix index out of range on zero layer metal load (#7696)
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:
parent
a14f76491d
commit
81d55d3e4d
1 changed files with 3 additions and 1 deletions
|
@ -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
|
||||
|
|
Loading…
Reference in a new issue