mirror of
https://github.com/ollama/ollama.git
synced 2026-04-20 07:54:25 +02:00
Add MLX runner with GLM4-MoE-Lite model support (#14185)
This change adds a new MLX based runner which includes: * Method-based MLX bindings * Subprocess-based MLX runner (x/mlxrunner) * KV cache with tree management * A basic sampler The GLM4-MoE-Lite model has been ported to use the new bindings. --------- Co-authored-by: Michael Yang <git@mxy.ng>
This commit is contained in:
17
x/mlxrunner/mlx/generator/generated.c.gotmpl
Normal file
17
x/mlxrunner/mlx/generator/generated.c.gotmpl
Normal file
@@ -0,0 +1,17 @@
|
||||
// This code is auto-generated; DO NOT EDIT.
|
||||
|
||||
#include "generated.h"
|
||||
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
{{ range .Functions }}
|
||||
{{ .Type }} (*{{ .Name }}_){{ .Parameters }} = NULL;
|
||||
{{- end }}
|
||||
|
||||
int mlx_dynamic_load_symbols(mlx_dynamic_handle handle) {
|
||||
{{- range .Functions }}
|
||||
CHECK_LOAD(handle, {{ .Name }});
|
||||
{{- end }}
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user