Search reviewed existing kernel sources before bounded custom-kernel experiments

curl --request POST \
  --url http://127.0.0.1:18000/api/v1/optimization/kernel-opportunities \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "hardware": {
    "accelerator": "<string>",
    "vendor": "nvidia",
    "compute_capability": "<string>"
  },
  "model": {
    "repository": "<string>",
    "revision": "<string>"
  },
  "policy": {},
  "profile": {},
  "runtime": {
    "image_digest": "<string>",
    "name": "<string>",
    "version": "<string>"
  },
  "schema_version": "infercrane.kernel-opportunity-request/v1",
  "workload": {
    "batch_size": 2,
    "concurrency": 2,
    "digest": "<string>",
    "input_tokens": 2,
    "output_tokens": 2
  }
}
'

import requests

url = "http://127.0.0.1:18000/api/v1/optimization/kernel-opportunities"

payload = {
    "hardware": {
        "accelerator": "<string>",
        "vendor": "nvidia",
        "compute_capability": "<string>"
    },
    "model": {
        "repository": "<string>",
        "revision": "<string>"
    },
    "policy": {},
    "profile": {},
    "runtime": {
        "image_digest": "<string>",
        "name": "<string>",
        "version": "<string>"
    },
    "schema_version": "infercrane.kernel-opportunity-request/v1",
    "workload": {
        "batch_size": 2,
        "concurrency": 2,
        "digest": "<string>",
        "input_tokens": 2,
        "output_tokens": 2
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    hardware: {accelerator: '<string>', vendor: 'nvidia', compute_capability: '<string>'},
    model: {repository: '<string>', revision: '<string>'},
    policy: {},
    profile: {},
    runtime: {image_digest: '<string>', name: '<string>', version: '<string>'},
    schema_version: 'infercrane.kernel-opportunity-request/v1',
    workload: {
      batch_size: 2,
      concurrency: 2,
      digest: '<string>',
      input_tokens: 2,
      output_tokens: 2
    }
  })
};

fetch('http://127.0.0.1:18000/api/v1/optimization/kernel-opportunities', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "http://127.0.0.1:18000/api/v1/optimization/kernel-opportunities"

	payload := strings.NewReader("{\n  \"hardware\": {\n    \"accelerator\": \"<string>\",\n    \"vendor\": \"nvidia\",\n    \"compute_capability\": \"<string>\"\n  },\n  \"model\": {\n    \"repository\": \"<string>\",\n    \"revision\": \"<string>\"\n  },\n  \"policy\": {},\n  \"profile\": {},\n  \"runtime\": {\n    \"image_digest\": \"<string>\",\n    \"name\": \"<string>\",\n    \"version\": \"<string>\"\n  },\n  \"schema_version\": \"infercrane.kernel-opportunity-request/v1\",\n  \"workload\": {\n    \"batch_size\": 2,\n    \"concurrency\": 2,\n    \"digest\": \"<string>\",\n    \"input_tokens\": 2,\n    \"output_tokens\": 2\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "category": "<string>",
    "remediation": "<string>",
    "request_id": "<string>",
    "retryable": true
  }
}