phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: update Cerebras inference provider to support dynamic model listing

Browse source 
- update Cerebras to use OpenAIMixin
- enable openai completions tests
- enable openai chat completions tests
- disable with n > 1 tests
- add recording for --setup cerebras --subdirs inference --pattern openai

test with: `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai`
This commit is contained in:
Matthew Farrellee 2025-09-18 06:34:31 -04:00
parent 521865c388
commit 1f7e87c647
16 changed files with 3369 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

146
tests/integration/recordings/responses/0648374e43e7.json Normal file
View file

@ -0,0 +1,146 @@
{
"request": {
"method": "POST",
"url": "https://api.cerebras.ai/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "llama-3.3-70b",
"messages": [
{
"role": "user",
"content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
}
],
"stream": true,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather in a given city",
"parameters": {
"type": "object",
"properties": {
"city": {
"type": "string",
"description": "The city to get the weather for"
}
}
}
}
}
]
},
"endpoint": "/v1/chat/completions",
"model": "llama-3.3-70b"
},
"response": {
"body": [
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "chatcmpl-8b6a9499-1a5f-46dc-96b7-3d2b71eecd99",
"choices": [
{
"delta": {
"content": null,
"function_call": null,
"refusal": null,
"role": "assistant",
"tool_calls": null
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 1758191362,
"model": "llama-3.3-70b",
"object": "chat.completion.chunk",
"service_tier": null,
"system_fingerprint": "fp_c5ec625e72d41732d8fd",
"usage": null
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "chatcmpl-8b6a9499-1a5f-46dc-96b7-3d2b71eecd99",
"choices": [
{
"delta": {
"content": null,
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": [
{
"index": 0,
"id": "439c86fe5",
"function": {
"arguments": "{\"city\": \"Tokyo\"}",
"name": "get_weather"
},
"type": "function"
}
]
},
"finish_reason": null,
"index": 0,
"logprobs": null
}
],
"created": 1758191362,
"model": "llama-3.3-70b",
"object": "chat.completion.chunk",
"service_tier": null,
"system_fingerprint": "fp_c5ec625e72d41732d8fd",
"usage": null
}
},
{
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
"__data__": {
"id": "chatcmpl-8b6a9499-1a5f-46dc-96b7-3d2b71eecd99",
"choices": [
{
"delta": {
"content": null,
"function_call": null,
"refusal": null,
"role": null,
"tool_calls": null
},
"finish_reason": "tool_calls",
"index": 0,
"logprobs": null
}
],
"created": 1758191362,
"model": "llama-3.3-70b",
"object": "chat.completion.chunk",
"service_tier": null,
"system_fingerprint": "fp_c5ec625e72d41732d8fd",
"usage": {
"completion_tokens": 12,
"prompt_tokens": 248,
"total_tokens": 260,
"completion_tokens_details": null,
"prompt_tokens_details": {
"audio_tokens": null,
"cached_tokens": 0
}
},
"time_info": {
"queue_time": 0.00016941,
"prompt_time": 0.007276727,
"completion_time": 0.00388514,
"total_time": 0.013146162033081055,
"created": 1758191362
}
}
}
],
"is_streaming": true
}
}