mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
# What does this PR do? - 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 Plan `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai` ``` tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] instantiating llama_stack_client Port 8321 is already in use, assuming server is already running... llama_stack_client instantiated in 0.053s PASSED [ 2%] tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=cerebras/llama-3.3-70b-inference:completion:suffix] SKIPPED (Suffix is not supported for the model: cerebras/llama-3.3-70b.) [ 4%] tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] PASSED [ 6%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=cerebras/llama-3.3-70b-1] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 8%] tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=cerebras/llama-3.3-70b] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 10%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] PASSED [ 12%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] PASSED [ 14%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cere...) [ 17%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-True] PASSED [ 19%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-True] PASSED [ 21%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=cerebras/llama-3.3-70b] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support chat completion calls wit...) [ 23%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 25%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 27%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 29%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 31%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 34%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 36%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 38%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 40%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 42%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 44%] tests/integration/inference/test_openai_completion.py::test_openai_completion_prompt_logprobs[txt=cerebras/llama-3.3-70b-0] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters.) [ 46%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_02] PASSED [ 48%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] PASSED [ 51%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote::cere...) [ 53%] tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-False] PASSED [ 55%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-False] PASSED [ 57%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 59%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 61%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 63%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 65%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 68%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 70%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 72%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 74%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 76%] tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-cerebras/llama-3.3-70b-None-None-None-384] SKIPPED (embedding_model_id empty - skipping test) [ 78%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] PASSED [ 80%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] PASSED [ 82%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_01] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote:...) [ 85%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-True] PASSED [ 87%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-True] PASSED [ 89%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_02] PASSED [ 91%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] PASSED [ 93%] tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] SKIPPED (Model cerebras/llama-3.3-70b hosted by remote:...) [ 95%] tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-False] PASSED [ 97%] tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-False] PASSED [100%] =================================================================================================================== slowest 10 durations ==================================================================================================================== 0.37s call tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=cerebras/llama-3.3-70b-inference:chat_completion:non_streaming_01] 0.34s call tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-False] 0.18s call tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=cerebras/llama-3.3-70b-True] 0.17s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=cerebras/llama-3.3-70b-inference:completion:sanity] 0.15s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-True] 0.13s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-True] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=cerebras/llama-3.3-70b-False] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=cerebras/llama-3.3-70b-True] 0.12s call tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=cerebras/llama-3.3-70b-False] 0.08s call tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=cerebras/llama-3.3-70b-inference:chat_completion:streaming_02] ================================================================================================================== short test summary info ================================================================================================================== SKIPPED [1] tests/integration/inference/test_openai_completion.py:75: Suffix is not supported for the model: cerebras/llama-3.3-70b. SKIPPED [3] tests/integration/inference/test_openai_completion.py:123: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support vllm extra_body parameters. SKIPPED [4] tests/integration/inference/test_openai_completion.py:103: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support n param. SKIPPED [1] tests/integration/inference/test_openai_completion.py:129: Model cerebras/llama-3.3-70b hosted by remote::cerebras doesn't support chat completion calls with base64 encoded files. SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:90: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:112: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:136: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:154: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:175: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:195: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:206: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:217: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:244: embedding_model_id empty - skipping test SKIPPED [2] tests/integration/inference/test_openai_embeddings.py:278: embedding_model_id empty - skipping test ================================================================================================= 18 passed, 29 skipped, 50 deselected, 4 warnings in 3.02s ================================================================================================= ```
146 lines
4.1 KiB
JSON
146 lines
4.1 KiB
JSON
{
|
|
"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
|
|
}
|
|
}
|