feat: add crds for vllm and llm examples #1766
feat: add crds for llm example, no planner
- Loading branch information
commit ec912faa33d5692ee6ba36bdacfc2717f9072264
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,92 @@ | ||
| apiVersion: nvidia.com/v1alpha1 | ||
| kind: DynamoGraphDeployment | ||
| metadata: | ||
| name: llm-agg | ||
| spec: | ||
| envs: | ||
| - name: DYN_DEPLOYMENT_CONFIG | ||
| 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.Processor.chat/completions","port":8000},"Processor":{"router":"round-robin","router-num-threads":4,"common-configs":["model","block-size","max-model-len"]},"VllmWorker":{"enforce-eager":true,"max-num-batched-tokens":16384,"enable-prefix-caching":true,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len"]},"Planner":{"environment":"kubernetes","no-operation":true}}' | ||
atchernych marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| services: | ||
| Frontend: | ||
| dynamoNamespace: llm-agg | ||
| componentType: main | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
atchernych marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| args: | ||
| - cd | ||
hhzhang16 marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg:Frontend | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Frontend | ||
| Processor: | ||
| dynamoNamespace: llm-agg | ||
| componentType: worker | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg:Processor | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Processor | ||
| VllmWorker: | ||
atchernych marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| envFromSecret: hf-token-secret | ||
| dynamoNamespace: llm-agg | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| limits: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg:VllmWorker | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - VllmWorker | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,119 @@ | ||
| apiVersion: nvidia.com/v1alpha1 | ||
| kind: DynamoGraphDeployment | ||
hhzhang16 marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| metadata: | ||
| name: agg-router | ||
| spec: | ||
| envs: | ||
| - name: DYN_DEPLOYMENT_CONFIG | ||
| value: '{"Common":{"model":"deepseek-ai/DeepSeek-R1-Distill-Llama-8B","router":"kv","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.Processor.chat/completions","port":8000},"Processor":{"common-configs":["model","block-size","max-model-len","router"]},"Router":{"min-workers":1,"softmax-sample":true,"common-configs":["model","block-size","router"]},"VllmWorker":{"enforce-eager":true,"max-num-batched-tokens":16384,"enable-prefix-caching":true,"tensor-parallel-size":1,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len","router","kv-transfer-config"]},"Planner":{"environment":"kubernetes","no-operation":true}}' | ||
| services: | ||
| Frontend: | ||
| dynamoNamespace: llm-agg-router | ||
| componentType: main | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg_router:Frontend | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Frontend | ||
| Processor: | ||
| dynamoNamespace: llm-agg-router | ||
| componentType: worker | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg_router:Processor | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Processor | ||
| Router: | ||
| dynamoNamespace: llm-agg-router | ||
| componentType: worker | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg_router:Router | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Router | ||
| VllmWorker: | ||
| envFromSecret: hf-token-secret | ||
| dynamoNamespace: llm-agg-router | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| limits: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| extraPodSpec: | ||
hhzhang16 marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.agg_router:VllmWorker | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - VllmWorker | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,121 @@ | ||
| apiVersion: nvidia.com/v1alpha1 | ||
| kind: DynamoGraphDeployment | ||
hhzhang16 marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| metadata: | ||
| name: llm-disagg | ||
| spec: | ||
| envs: | ||
| - name: DYN_DEPLOYMENT_CONFIG | ||
| 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.Processor.chat/completions","port":8000},"Processor":{"router":"round-robin","common-configs":["model","block-size"]},"VllmWorker":{"remote-prefill":true,"conditional-disagg":true,"max-local-prefill-length":10,"max-prefill-queue-size":2,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"PrefillWorker":{"max-num-batched-tokens":16384,"ServiceArgs":{"workers":1,"resources":{"gpu":"1"}},"common-configs":["model","block-size","max-model-len","kv-transfer-config"]},"Planner":{"environment":"kubernetes","no-operation":true}}' | ||
| services: | ||
| Frontend: | ||
| dynamoNamespace: llm-disagg | ||
| componentType: main | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.disagg:Frontend | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Frontend | ||
| Processor: | ||
| dynamoNamespace: llm-disagg | ||
| componentType: worker | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| limits: | ||
| cpu: "1" | ||
| memory: "2Gi" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.disagg:Processor | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - Processor | ||
| VllmWorker: | ||
| envFromSecret: hf-token-secret | ||
| dynamoNamespace: llm-disagg | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| limits: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
hhzhang16 marked this conversation as resolved.
Outdated
Show resolved
Hide resolved
|
||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.disagg:VllmWorker | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - VllmWorker | ||
| PrefillWorker: | ||
| envFromSecret: hf-token-secret | ||
| dynamoNamespace: llm-disagg | ||
| replicas: 1 | ||
| resources: | ||
| requests: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| limits: | ||
| cpu: "10" | ||
| memory: "20Gi" | ||
| gpu: "1" | ||
| extraPodSpec: | ||
| mainContainer: | ||
| image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.3.1 | ||
| args: | ||
| - cd | ||
| - /workspace/examples/llm | ||
| - "&&" | ||
| - dynamo | ||
| - serve | ||
| - graphs.disagg:PrefillWorker | ||
| - --system-app-port | ||
| - "5000" | ||
| - --enable-system-app | ||
| - --use-default-health-checks | ||
| - --service-name | ||
| - PrefillWorker | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.