OSSForks/ollama
1
0
Fork 0
mirror of https://github.com/zebrajr/ollama.git synced 2025-12-06 00:19:51 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

ggml: Check return status for computation.

Browse Source 
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:
Jesse Gross 2025-06-19 14:39:20 -07:00 committed by Jesse Gross
parent f2527b08fb
commit 87b7af6cee
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ml/backend/ggml/ggml.go
View File

@ -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