highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-10 11:47:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #9824 from ollama/mxyng/sched

Browse Source 
conditionally enable parallel pipelines
This commit is contained in:
Michael Yang
2025-03-17 15:41:37 -07:00
committed by GitHub
parent bf24498b1e 4561fff36e
commit 021dcf089d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ml/backend/ggml/ggml.go
View File

@@ -373,7 +373,7 @@ func New(r *os.File, params ml.BackendParams) (ml.Backend, error) {
(*C.ggml_backend_buffer_type_t)(unsafe.Pointer(&schedBufts[0])),
C.int(len(schedBackends)),
C.size_t(maxGraphNodes),
true,
C._Bool(len(gpus) > 1 && slices.Contains(gpus, output.d)),
),
input: deviceBufferTypes[input.d],
output: deviceBufferTypes[output.d],