mlboydaisuke commited on
Commit
2d7f93a
·
verified ·
1 Parent(s): 7f8783c

iOS GPU best: fp16 static ctx-2048 monolith (27.7 tok/s)

Browse files
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  dynamic-int8/qwen3_5_0_8b_decode_int8.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
37
  ios-gpu-static/qwen3_5_0_8b_ios_hc0.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  dynamic-int8/qwen3_5_0_8b_decode_int8.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
37
  ios-gpu-static/qwen3_5_0_8b_ios_hc0.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
38
+ ios-gpu/qwen3_5_0_8b_ios_hc0.aimodel/main.mlirb filter=lfs diff=lfs merge=lfs -text
ios-gpu/qwen3_5_0_8b_ios_hc0.aimodel/main.hash ADDED
@@ -0,0 +1 @@
 
 
1
+ ��✓w��a܃
ios-gpu/qwen3_5_0_8b_ios_hc0.aimodel/main.mlirb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8fae29c9377018be061dc830dec7e5ae588e820e8a1a89a3c95a84e66f40c2c
3
+ size 1505260435
ios-gpu/qwen3_5_0_8b_ios_hc0.aimodel/metadata.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "assetVersion" : "2.0"
3
+ }