mirror of
https://github.com/ollama/ollama.git
synced 2025-07-28 18:23:56 +02:00
ggml: Check return status for computation.
We don't check the return status after computing the graph, which can silently lead to bad outputs if we try to keep going and future computation succeeds. This appears to happens in certain cases on Apple M2 devices. Fixes #11070
This commit is contained in:
@@ -602,7 +602,9 @@ func (c *Context) Forward(tensors ...ml.Tensor) ml.Context {
|
||||
}
|
||||
|
||||
func (c *Context) Compute(tensors ...ml.Tensor) {
|
||||
C.ggml_backend_sched_graph_compute_async(c.b.sched, c.graph)
|
||||
if status := C.ggml_backend_sched_graph_compute_async(c.b.sched, c.graph); status != C.GGML_STATUS_SUCCESS {
|
||||
panic(fmt.Errorf("error computing ggml graph: %v", status))
|
||||
}
|
||||
C.ggml_backend_sched_reset(c.b.sched)
|
||||
|
||||
needSync := true
|
||||
|
Reference in New Issue
Block a user