@aws/ml-container-creator 0.9.0 → 0.10.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (48) hide show
  1. package/bin/cli.js +31 -137
  2. package/config/parameter-schema-v2.json +2065 -0
  3. package/package.json +6 -3
  4. package/servers/lib/catalogs/jumpstart-public.json +101 -16
  5. package/servers/lib/catalogs/models.json +182 -26
  6. package/src/app.js +6 -389
  7. package/src/lib/bootstrap-command-handler.js +75 -1078
  8. package/src/lib/bootstrap-profile-manager.js +634 -0
  9. package/src/lib/bootstrap-provisioners.js +421 -0
  10. package/src/lib/config-loader.js +405 -0
  11. package/src/lib/config-manager.js +59 -1668
  12. package/src/lib/config-mcp-client.js +118 -0
  13. package/src/lib/config-validator.js +634 -0
  14. package/src/lib/cuda-resolver.js +140 -0
  15. package/src/lib/e2e-catalog-validator.js +251 -3
  16. package/src/lib/e2e-ci-recorder.js +103 -0
  17. package/src/lib/generated/cli-options.js +471 -0
  18. package/src/lib/generated/parameter-matrix.js +671 -0
  19. package/src/lib/generated/validation-rules.js +202 -0
  20. package/src/lib/marketplace-flow.js +276 -0
  21. package/src/lib/mcp-query-runner.js +768 -0
  22. package/src/lib/parameter-schema-validator.js +62 -18
  23. package/src/lib/prompt-runner.js +41 -1504
  24. package/src/lib/prompts/feature-prompts.js +172 -0
  25. package/src/lib/prompts/index.js +48 -0
  26. package/src/lib/prompts/infrastructure-prompts.js +690 -0
  27. package/src/lib/prompts/model-prompts.js +552 -0
  28. package/src/lib/prompts/project-prompts.js +70 -0
  29. package/src/lib/prompts.js +2 -1446
  30. package/src/lib/registry-command-handler.js +135 -3
  31. package/src/lib/secrets-prompt-runner.js +251 -0
  32. package/src/lib/template-variable-resolver.js +398 -0
  33. package/templates/code/serve +5 -134
  34. package/templates/code/serve.d/lmi.ejs +19 -0
  35. package/templates/code/serve.d/sglang.ejs +47 -0
  36. package/templates/code/serve.d/tensorrt-llm.ejs +53 -0
  37. package/templates/code/serve.d/vllm.ejs +48 -0
  38. package/templates/do/clean +1 -1387
  39. package/templates/do/clean.d/async-inference.ejs +508 -0
  40. package/templates/do/clean.d/batch-transform.ejs +512 -0
  41. package/templates/do/clean.d/hyperpod-eks.ejs +481 -0
  42. package/templates/do/clean.d/managed-inference.ejs +1043 -0
  43. package/templates/do/deploy +1 -1766
  44. package/templates/do/deploy.d/async-inference.ejs +501 -0
  45. package/templates/do/deploy.d/batch-transform.ejs +529 -0
  46. package/templates/do/deploy.d/hyperpod-eks.ejs +339 -0
  47. package/templates/do/deploy.d/managed-inference.ejs +726 -0
  48. package/config/parameter-schema.json +0 -88
package/config/parameter-schema.json DELETED
@@ -1,88 +0,0 @@
1
- {
2
- "schemaVersion": "1.0.0",
3
- "deploymentTargets": {
4
- "realtime-inference": {
5
- "endpoint": {
6
- "initialInstanceCount": {
7
- "type": "integer",
8
- "min": 1,
9
- "max": 100,
10
- "default": 1,
11
- "description": "Number of instances for the endpoint",
12
- "apiReference": "CreateEndpointConfig.ProductionVariants.InitialInstanceCount"
13
- },
14
- "dataCapturePercent": {
15
- "type": "integer",
16
- "min": 0,
17
- "max": 100,
18
- "default": 0,
19
- "description": "Percentage of requests to capture",
20
- "apiReference": "CreateEndpointConfig.DataCaptureConfig.InitialSamplingPercentage"
21
- },
22
- "variantName": {
23
- "type": "string",
24
- "pattern": "^[a-zA-Z0-9]([\\w-]{0,62}[a-zA-Z0-9])?$",
25
- "default": "AllTraffic",
26
- "description": "Name of the production variant",
27
- "apiReference": "CreateEndpointConfig.ProductionVariants.VariantName"
28
- },
29
- "volumeSize": {
30
- "type": "integer",
31
- "min": 1,
32
- "max": 16384,
33
- "default": null,
34
- "description": "Size of the ML storage volume in GB",
35
- "apiReference": "CreateEndpointConfig.ProductionVariants.VolumeSizeInGB"
36
- }
37
- },
38
- "inferenceComponent": {
39
- "cpuCount": {
40
- "type": "number",
41
- "min": 0.25,
42
- "max": 768,
43
- "default": null,
44
- "description": "Number of vCPUs allocated",
45
- "apiReference": "CreateInferenceComponent.Specification.ComputeResourceRequirements.NumberOfCpuCoresRequired"
46
- },
47
- "memorySize": {
48
- "type": "integer",
49
- "min": 128,
50
- "max": 3145728,
51
- "default": null,
52
- "description": "Memory allocation in MB",
53
- "apiReference": "CreateInferenceComponent.Specification.ComputeResourceRequirements.MinMemoryRequiredInMb"
54
- },
55
- "gpuCount": {
56
- "type": "integer",
57
- "min": 0,
58
- "max": 8,
59
- "default": null,
60
- "description": "Number of GPUs allocated",
61
- "apiReference": "CreateInferenceComponent.Specification.ComputeResourceRequirements.NumberOfAcceleratorDevicesRequired"
62
- },
63
- "copyCount": {
64
- "type": "integer",
65
- "min": 0,
66
- "max": 100,
67
- "default": 1,
68
- "description": "Number of inference component copies",
69
- "apiReference": "CreateInferenceComponent.RuntimeConfig.CopyCount"
70
- },
71
- "modelWeight": {
72
- "type": "number",
73
- "min": 0,
74
- "max": 1,
75
- "default": 1.0,
76
- "description": "Traffic routing weight for the model",
77
- "apiReference": "UpdateEndpointWeightsAndCapacities.DesiredWeightsAndCapacities.DesiredWeight"
78
- }
79
- }
80
- },
81
- "eks": {},
82
- "async": {},
83
- "batch": {}
84
- },
85
- "extensionPoints": {
86
- "engines": {}
87
- }
88
- }