Skip to content

Commit a5ec55f

Browse files
adjust qwen runtimes to vllm
1 parent 12ed0ea commit a5ec55f

38 files changed

Lines changed: 3651 additions & 15 deletions

config/runtimes/srt/Qwen/qwen-text-tp1-fp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp1-fp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp1-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp1
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp2-fp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp2-fp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp2-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp2
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp4-fp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp4-fp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp4-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp4
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-text-tp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-text-tp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-vl-tp1-fp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-vl-tp1-fp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-vl-tp1-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-vl-tp1
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

config/runtimes/srt/Qwen/qwen-vl-tp2-fp8-rt.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ kind: ClusterServingRuntime
33
metadata:
44
name: srt-qwen-vl-tp2-fp8
55
spec:
6-
disabled: false
6+
disabled: true
77
supportedModelFormats:
88
- modelFramework:
99
name: transformers

0 commit comments

Comments
 (0)