Unverified Commit b2aa2317 authored by julienmancuso's avatar julienmancuso Committed by GitHub
Browse files

feat: deploy planner in operator (#921)


Co-authored-by: default avatarmohammedabdulwahhab <furkhan324@berkeley.edu>
parent 57975b27
...@@ -36,3 +36,7 @@ VllmWorker: ...@@ -36,3 +36,7 @@ VllmWorker:
resources: resources:
gpu: 1 gpu: 1
common-configs: [model, block-size, max-model-len] common-configs: [model, block-size, max-model-len]
Planner:
environment: local
no-operation: true
\ No newline at end of file
...@@ -41,3 +41,7 @@ VllmWorker: ...@@ -41,3 +41,7 @@ VllmWorker:
resources: resources:
gpu: 1 gpu: 1
common-configs: [model, block-size, max-model-len, router, kv-transfer-config] common-configs: [model, block-size, max-model-len, router, kv-transfer-config]
Planner:
environment: local
no-operation: true
\ No newline at end of file
...@@ -45,3 +45,7 @@ PrefillWorker: ...@@ -45,3 +45,7 @@ PrefillWorker:
resources: resources:
gpu: 1 gpu: 1
common-configs: [model, block-size, max-model-len, kv-transfer-config] common-configs: [model, block-size, max-model-len, kv-transfer-config]
Planner:
environment: local
no-operation: true
\ No newline at end of file
...@@ -52,3 +52,7 @@ PrefillWorker: ...@@ -52,3 +52,7 @@ PrefillWorker:
resources: resources:
gpu: 1 gpu: 1
common-configs: [model, block-size, max-model-len, kv-transfer-config] common-configs: [model, block-size, max-model-len, kv-transfer-config]
Planner:
environment: local
no-operation: true
\ No newline at end of file
...@@ -14,7 +14,9 @@ ...@@ -14,7 +14,9 @@
# limitations under the License. # limitations under the License.
from components.frontend import Frontend from components.frontend import Frontend
from components.planner_service import Planner
from components.processor import Processor from components.processor import Processor
from components.worker import VllmWorker from components.worker import VllmWorker
Frontend.link(Processor).link(VllmWorker) Frontend.link(Processor).link(VllmWorker)
Frontend.link(Planner)
...@@ -15,7 +15,9 @@ ...@@ -15,7 +15,9 @@
from components.frontend import Frontend from components.frontend import Frontend
from components.kv_router import Router from components.kv_router import Router
from components.planner_service import Planner
from components.processor import Processor from components.processor import Processor
from components.worker import VllmWorker from components.worker import VllmWorker
Frontend.link(Processor).link(Router).link(VllmWorker) Frontend.link(Processor).link(Router).link(VllmWorker)
Frontend.link(Planner)
...@@ -14,8 +14,10 @@ ...@@ -14,8 +14,10 @@
# limitations under the License. # limitations under the License.
from components.frontend import Frontend from components.frontend import Frontend
from components.planner_service import Planner
from components.prefill_worker import PrefillWorker from components.prefill_worker import PrefillWorker
from components.processor import Processor from components.processor import Processor
from components.worker import VllmWorker from components.worker import VllmWorker
Frontend.link(Processor).link(VllmWorker).link(PrefillWorker) Frontend.link(Processor).link(VllmWorker).link(PrefillWorker)
Frontend.link(Planner)
...@@ -15,8 +15,10 @@ ...@@ -15,8 +15,10 @@
from components.frontend import Frontend from components.frontend import Frontend
from components.kv_router import Router from components.kv_router import Router
from components.planner_service import Planner
from components.prefill_worker import PrefillWorker from components.prefill_worker import PrefillWorker
from components.processor import Processor from components.processor import Processor
from components.worker import VllmWorker from components.worker import VllmWorker
Frontend.link(Processor).link(Router).link(VllmWorker).link(PrefillWorker) Frontend.link(Processor).link(Router).link(VllmWorker).link(PrefillWorker)
Frontend.link(Planner)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment