Skip to content
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
feat: update namespaces
  • Loading branch information
hhzhang16 committed Jul 3, 2025
commit 1a09de800d531f28a114c03bee12d0e60cc0825d
6 changes: 3 additions & 3 deletions examples/vllm_v0/deploy/agg.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ spec:
value: '{"Common":{"model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","block-size":64,"max-model-len":16384},"Frontend":{"served_model_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","endpoint":"dynamo.VllmWorker.generate","port":8000,"router":"round-robin","common-configs":["block-size"]},"VllmWorker":{"enforce-eager":true,"max-num-batched-tokens":16384,"enable-prefix-caching":true,"common-configs":["model","block-size","max-model-len"]}}'
services:
Frontend:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-agg
componentType: main
replicas: 1
resources:
Expand Down Expand Up @@ -36,7 +36,7 @@ spec:
- Frontend
VllmWorker:
envFromSecret: hf-token-secret
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-agg
replicas: 1
resources:
requests:
Expand All @@ -62,4 +62,4 @@ spec:
- --enable-system-app
- --use-default-health-checks
- --service-name
- VllmWorker
- VllmWorker
8 changes: 4 additions & 4 deletions examples/vllm_v0/deploy/disagg.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ spec:
value: '{"Common":{"model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","block-size":64,"max-model-len":16384,"kv-transfer-config":"{\"kv_connector\":\"DynamoNixlConnector\"}"},"Frontend":{"served_model_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","endpoint":"dynamo.VllmWorker.generate","port":8000,"router":"round-robin","common-configs":["block-size"]},"VllmWorker":{"remote-prefill":true,"conditional-disagg":true,"max-local-prefill-length":10,"max-prefill-queue-size":2,"enable-prefix-caching":true,"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"PrefillWorker":{"max-num-batched-tokens":16384,"common-configs":["model","block-size","max-model-len","kv-transfer-config"]}}'
services:
Frontend:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg
componentType: main
replicas: 1
resources:
Expand All @@ -35,7 +35,7 @@ spec:
- --service-name
- Frontend
VllmWorker:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg
envFromSecret: hf-token-secret
replicas: 1
resources:
Expand Down Expand Up @@ -64,7 +64,7 @@ spec:
- --service-name
- VllmWorker
PrefillWorker:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg
envFromSecret: hf-token-secret
replicas: 1
resources:
Expand All @@ -91,4 +91,4 @@ spec:
- --enable-system-app
- --use-default-health-checks
- --service-name
- PrefillWorker
- PrefillWorker
12 changes: 6 additions & 6 deletions examples/vllm_v0/deploy/disagg_planner.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ spec:
value: '{"Common":{"model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","block-size":64,"max-model-len":16384,"kv-transfer-config":"{\"kv_connector\":\"DynamoNixlConnector\"}"},"Frontend":{"served_model_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","endpoint":"dynamo.VllmWorker.generate","port":8000,"router":"round-robin","common-configs":["block-size"]},"VllmWorker":{"remote-prefill":true,"conditional-disagg":true,"max-local-prefill-length":10,"max-prefill-queue-size":2,"enable-prefix-caching":true,"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"PrefillWorker":{"max-num-batched-tokens":16384,"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"Prometheus":{"global":{"scrape_interval":"5s"},"scrape_configs":[{"job_name":"prometheus","static_configs":[{"targets":["localhost:9090"]}]},{"job_name":"frontend","static_configs":[{"targets":["localhost:8000"]}]}]},"Planner":{"adjustment-interval":180,"profile-results-dir":"/workspace/examples/profiling_results","isl":3000,"osl":150,"ttft":0.5,"itl":0.05,"load-predictor":"arima"}}'
services:
Frontend:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg-planner
componentType: main
replicas: 1
resources:
Expand Down Expand Up @@ -36,7 +36,7 @@ spec:
- Frontend

VllmWorker:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg-planner
envFromSecret: hf-token-secret
replicas: 1
resources:
Expand Down Expand Up @@ -66,7 +66,7 @@ spec:
- VllmWorker

PrefillWorker:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg-planner
envFromSecret: hf-token-secret
replicas: 1
resources:
Expand Down Expand Up @@ -96,7 +96,7 @@ spec:
- PrefillWorker

Planner:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg-planner
replicas: 1
componentType: planner
resources:
Expand Down Expand Up @@ -125,7 +125,7 @@ spec:
- --Planner.environment=kubernetes

Prometheus:
dynamoNamespace: dynamo
dynamoNamespace: vllm-v0-disagg-planner
replicas: 1
resources:
requests:
Expand All @@ -149,4 +149,4 @@ spec:
- --enable-system-app
- --use-default-health-checks
- --service-name
- Prometheus
- Prometheus
Loading