OpenAI APIs - Completions#

SGLang provides OpenAI-compatible APIs to enable a smooth transition from OpenAI services to self-hosted local models. A complete reference for the API is available in the OpenAI API Reference.

This tutorial covers the following popular APIs:

chat/completions
completions
batches

Check out other tutorials to learn about vision APIs for vision-language models and embedding APIs for embedding models.

Launch A Server#

Launch the server in your terminal and wait for it to initialize.

[1]:

from sglang.test.test_utils import is_in_ci

if is_in_ci():
    from patch import launch_server_cmd
else:
    from sglang.utils import launch_server_cmd

from sglang.utils import wait_for_server, print_highlight, terminate_process


server_process, port = launch_server_cmd(
    "python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-8B-Instruct --host 0.0.0.0"
)

wait_for_server(f"http://localhost:{port}")
print(f"Server started on http://localhost:{port}")

[2025-04-13 23:25:45] server_args=ServerArgs(model_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_path='meta-llama/Meta-Llama-3.1-8B-Instruct', tokenizer_mode='auto', skip_tokenizer_init=False, load_format='auto', trust_remote_code=False, dtype='auto', kv_cache_dtype='auto', quantization=None, quantization_param_path=None, context_length=None, device='cuda', served_model_name='meta-llama/Meta-Llama-3.1-8B-Instruct', chat_template=None, completion_template=None, is_embedding=False, revision=None, host='0.0.0.0', port=38464, mem_fraction_static=0.88, max_running_requests=200, max_total_tokens=20480, chunked_prefill_size=8192, max_prefill_tokens=16384, schedule_policy='fcfs', schedule_conservativeness=1.0, cpu_offload_gb=0, page_size=1, tp_size=1, stream_interval=1, stream_output=False, random_seed=626861021, constrained_json_whitespace_pattern=None, watchdog_timeout=300, dist_timeout=None, download_dir=None, base_gpu_id=0, gpu_id_step=1, log_level='info', log_level_http=None, log_requests=False, log_requests_level=0, show_time_cost=False, enable_metrics=False, decode_log_interval=40, api_key=None, file_storage_path='sglang_storage', enable_cache_report=False, reasoning_parser=None, dp_size=1, load_balance_method='round_robin', ep_size=1, dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', lora_paths=None, max_loras_per_batch=8, lora_backend='triton', attention_backend=None, sampling_backend='flashinfer', grammar_backend='xgrammar', speculative_algorithm=None, speculative_draft_model_path=None, speculative_num_steps=None, speculative_eagle_topk=None, speculative_num_draft_tokens=None, speculative_accept_threshold_single=1.0, speculative_accept_threshold_acc=1.0, speculative_token_map=None, enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, disable_radix_cache=False, disable_cuda_graph=True, disable_cuda_graph_padding=False, enable_nccl_nvls=False, disable_outlines_disk_cache=False, disable_custom_all_reduce=False, disable_mla=False, enable_llama4_multimodal=None, disable_overlap_schedule=False, enable_mixed_chunk=False, enable_dp_attention=False, enable_ep_moe=False, enable_deepep_moe=False, deepep_mode='auto', enable_torch_compile=False, torch_compile_max_bs=32, cuda_graph_max_bs=160, cuda_graph_bs=None, torchao_config='', enable_nan_detection=False, enable_p2p_check=False, triton_attention_reduce_in_fp32=False, triton_attention_num_kv_splits=8, num_continuous_decode_steps=1, delete_ckpt_after_loading=False, enable_memory_saver=False, allow_auto_truncate=False, enable_custom_logit_processor=False, tool_call_parser=None, enable_hierarchical_cache=False, hicache_ratio=2.0, enable_flashinfer_mla=False, enable_flashmla=False, flashinfer_mla_disable_ragged=False, warmups=None, n_share_experts_fusion=0, disable_shared_experts_fusion=False, debug_tensor_dump_output_folder=None, debug_tensor_dump_input_file=None, debug_tensor_dump_inject=False, disaggregation_mode='null', disaggregation_bootstrap_port=8998, disaggregation_transfer_backend='mooncake', disable_fast_image_processor=False)
[2025-04-13 23:25:57 TP0] Attention backend not set. Use flashinfer backend by default.
[2025-04-13 23:25:57 TP0] Init torch distributed begin.
[2025-04-13 23:25:57 TP0] Init torch distributed ends. mem usage=0.00 GB
[2025-04-13 23:25:57 TP0] Load weight begin. avail mem=44.53 GB
[2025-04-13 23:25:57 TP0] Ignore import error when loading sglang.srt.models.llama4.
[2025-04-13 23:25:58 TP0] Using model weights format ['*.safetensors']
Loading safetensors checkpoint shards:   0% Completed | 0/4 [00:00<?, ?it/s]
Loading safetensors checkpoint shards:  25% Completed | 1/4 [00:00<00:02,  1.41it/s]
Loading safetensors checkpoint shards:  50% Completed | 2/4 [00:01<00:01,  1.32it/s]
Loading safetensors checkpoint shards:  75% Completed | 3/4 [00:02<00:00,  1.32it/s]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:02<00:00,  1.79it/s]
Loading safetensors checkpoint shards: 100% Completed | 4/4 [00:02<00:00,  1.59it/s]

[2025-04-13 23:26:01 TP0] Load weight end. type=LlamaForCausalLM, dtype=torch.bfloat16, avail mem=46.43 GB, mem usage=-1.91 GB.
[2025-04-13 23:26:01 TP0] KV Cache is allocated. #tokens: 20480, K size: 1.25 GB, V size: 1.25 GB
[2025-04-13 23:26:01 TP0] Memory pool end. avail mem=43.64 GB
[2025-04-13 23:26:01 TP0]

CUDA Graph is DISABLED.
This will cause significant performance degradation.
CUDA Graph should almost never be disabled in most usage scenarios.
If you encounter OOM issues, please try setting --mem-fraction-static to a lower value (such as 0.8 or 0.7) instead of disabling CUDA Graph.

[2025-04-13 23:26:01 TP0] max_total_num_tokens=20480, chunked_prefill_size=8192, max_prefill_tokens=16384, max_running_requests=200, context_len=131072
[2025-04-13 23:26:02] INFO:     Started server process [2788024]
[2025-04-13 23:26:02] INFO:     Waiting for application startup.
[2025-04-13 23:26:02] INFO:     Application startup complete.
[2025-04-13 23:26:02] INFO:     Uvicorn running on http://0.0.0.0:38464 (Press CTRL+C to quit)
[2025-04-13 23:26:02] INFO:     127.0.0.1:49074 - "GET /v1/models HTTP/1.1" 200 OK
[2025-04-13 23:26:03] INFO:     127.0.0.1:49090 - "GET /get_model_info HTTP/1.1" 200 OK
[2025-04-13 23:26:03 TP0] Prefill batch. #new-seq: 1, #new-token: 7, #cached-token: 0, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:06] INFO:     127.0.0.1:49098 - "POST /generate HTTP/1.1" 200 OK
[2025-04-13 23:26:06] The server is fired up and ready to roll!

NOTE: Typically, the server runs in a separate terminal.
In this notebook, we run the server and notebook code together, so their outputs are combined.
To improve clarity, the server logs are displayed in the original black color, while the notebook outputs are highlighted in blue.
We are running those notebooks in a CI parallel environment, so the throughput is not representative of the actual performance.

Server started on http://localhost:38464

Chat Completions#

Usage#

The server fully implements the OpenAI API. It will automatically apply the chat template specified in the Hugging Face tokenizer, if one is available. You can also specify a custom chat template with --chat-template when launching the server.

[2]:

import openai

client = openai.Client(base_url=f"http://127.0.0.1:{port}/v1", api_key="None")

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {"role": "user", "content": "List 3 countries and their capitals."},
    ],
    temperature=0,
    max_tokens=64,
)

print_highlight(f"Response: {response}")

[2025-04-13 23:26:08 TP0] Prefill batch. #new-seq: 1, #new-token: 42, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:08 TP0] Decode batch. #running-req: 1, #token: 76, token usage: 0.00, gen throughput (token/s): 6.00, #queue-req: 0,
[2025-04-13 23:26:08] INFO:     127.0.0.1:49108 - "POST /v1/chat/completions HTTP/1.1" 200 OK

Response: ChatCompletion(id='61742c25950b4fe79e5d832d69cd9c70', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='Here are 3 countries and their capitals:\n\n1. Country: Japan\n Capital: Tokyo\n\n2. Country: Australia\n Capital: Canberra\n\n3. Country: Brazil\n Capital: Brasília', refusal=None, role='assistant', annotations=None, audio=None, function_call=None, tool_calls=None, reasoning_content=None), matched_stop=128009)], created=1744586768, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='chat.completion', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=43, prompt_tokens=43, total_tokens=86, completion_tokens_details=None, prompt_tokens_details=None))

Parameters#

The chat completions API accepts OpenAI Chat Completions API’s parameters. Refer to OpenAI Chat Completions API for more details.

Here is an example of a detailed chat completion request:

[3]:

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[
        {
            "role": "system",
            "content": "You are a knowledgeable historian who provides concise responses.",
        },
        {"role": "user", "content": "Tell me about ancient Rome"},
        {
            "role": "assistant",
            "content": "Ancient Rome was a civilization centered in Italy.",
        },
        {"role": "user", "content": "What were their major achievements?"},
    ],
    temperature=0.3,  # Lower temperature for more focused responses
    max_tokens=128,  # Reasonable length for a concise response
    top_p=0.95,  # Slightly higher for better fluency
    presence_penalty=0.2,  # Mild penalty to avoid repetition
    frequency_penalty=0.2,  # Mild penalty for more natural language
    n=1,  # Single response is usually more stable
    seed=42,  # Keep for reproducibility
)

print_highlight(response.choices[0].message.content)

[2025-04-13 23:26:08 TP0] Prefill batch. #new-seq: 1, #new-token: 51, #cached-token: 25, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:09 TP0] Decode batch. #running-req: 1, #token: 106, token usage: 0.01, gen throughput (token/s): 55.56, #queue-req: 0,
[2025-04-13 23:26:10 TP0] Decode batch. #running-req: 1, #token: 146, token usage: 0.01, gen throughput (token/s): 62.08, #queue-req: 0,
[2025-04-13 23:26:10 TP0] Decode batch. #running-req: 1, #token: 186, token usage: 0.01, gen throughput (token/s): 60.03, #queue-req: 0,
[2025-04-13 23:26:10] INFO:     127.0.0.1:49108 - "POST /v1/chat/completions HTTP/1.1" 200 OK

Ancient Rome's major achievements include:

1. **Engineering and Architecture**: Romans developed concrete, aqueducts, roads (e.g., Appian Way), and iconic structures like the Colosseum, Pantheon, and Roman Forum.
2. **Law and Governance**: They established the Twelve Tables (450 BCE), a precursor to modern law, and the Roman Republic's system of governance, which influenced Western democracy.
3. **Military Conquests**: Rome expanded its territories through a series of wars, creating a vast empire that lasted for centuries (264 BCE - 476 CE).
4. **Language and Literature**: Latin became the

Streaming mode is also supported.

[4]:

stream = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True,
)
for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")

[2025-04-13 23:26:10] INFO:     127.0.0.1:49108 - "POST /v1/chat/completions HTTP/1.1" 200 OK
[2025-04-13 23:26:10 TP0] Prefill batch. #new-seq: 1, #new-token: 10, #cached-token: 30, token usage: 0.00, #running-req: 0, #queue-req: 0,
This is only a test.

Completions#

Usage#

Completions API is similar to Chat Completions API, but without the messages parameter or chat templates.

[5]:

response = client.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    prompt="List 3 countries and their capitals.",
    temperature=0,
    max_tokens=64,
    n=1,
    stop=None,
)

print_highlight(f"Response: {response}")

[2025-04-13 23:26:11 TP0] Prefill batch. #new-seq: 1, #new-token: 8, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:11 TP0] Decode batch. #running-req: 1, #token: 24, token usage: 0.00, gen throughput (token/s): 55.87, #queue-req: 0,
[2025-04-13 23:26:12 TP0] Decode batch. #running-req: 1, #token: 64, token usage: 0.00, gen throughput (token/s): 63.14, #queue-req: 0,
[2025-04-13 23:26:12] INFO:     127.0.0.1:49108 - "POST /v1/completions HTTP/1.1" 200 OK

Response: Completion(id='ef09df1a9a7b4e7e8f886faf1a2e9a86', choices=[CompletionChoice(finish_reason='length', index=0, logprobs=None, text=' 1. 2. 3.\n1. United States - Washington D.C. 2. Japan - Tokyo 3. Australia - Canberra\nList 3 countries and their capitals. 1. 2. 3.\n1. China - Beijing 2. Brazil - Bras', matched_stop=None)], created=1744586771, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='text_completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=64, prompt_tokens=9, total_tokens=73, completion_tokens_details=None, prompt_tokens_details=None))

Parameters#

The completions API accepts OpenAI Completions API’s parameters. Refer to OpenAI Completions API for more details.

Here is an example of a detailed completions request:

[6]:

response = client.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    prompt="Write a short story about a space explorer.",
    temperature=0.7,  # Moderate temperature for creative writing
    max_tokens=150,  # Longer response for a story
    top_p=0.9,  # Balanced diversity in word choice
    stop=["\n\n", "THE END"],  # Multiple stop sequences
    presence_penalty=0.3,  # Encourage novel elements
    frequency_penalty=0.3,  # Reduce repetitive phrases
    n=1,  # Generate one completion
    seed=123,  # For reproducible results
)

print_highlight(f"Response: {response}")

[2025-04-13 23:26:12 TP0] Prefill batch. #new-seq: 1, #new-token: 9, #cached-token: 1, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:12 TP0] Decode batch. #running-req: 1, #token: 41, token usage: 0.00, gen throughput (token/s): 78.52, #queue-req: 0,
[2025-04-13 23:26:12] INFO:     127.0.0.1:49108 - "POST /v1/completions HTTP/1.1" 200 OK

Response: Completion(id='cece010a10524b278487b2a3b5905b8b', choices=[CompletionChoice(finish_reason='stop', index=0, logprobs=None, text=' The story should be a mystery, and it\'s a "what happened to..." type of tale. The last sentence is the broken record that repeats at the end of every episode of the "What Happened to...?" series.', matched_stop='\n\n')], created=1744586772, model='meta-llama/Meta-Llama-3.1-8B-Instruct', object='text_completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=48, prompt_tokens=10, total_tokens=58, completion_tokens_details=None, prompt_tokens_details=None))

Structured Outputs (JSON, Regex, EBNF)#

For OpenAI compatible structed outputs API, refer to Structured Outputs for more details.

Batches#

Batches API for chat completions and completions are also supported. You can upload your requests in jsonl files, create a batch job, and retrieve the results when the batch job is completed (which takes longer but costs less).

The batches APIs are:

batches
batches/{batch_id}/cancel
batches/{batch_id}

Here is an example of a batch job for chat completions, completions are similar.

[7]:

import json
import time
from openai import OpenAI

client = OpenAI(base_url=f"http://127.0.0.1:{port}/v1", api_key="None")

requests = [
    {
        "custom_id": "request-1",
        "method": "POST",
        "url": "/chat/completions",
        "body": {
            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
            "messages": [
                {"role": "user", "content": "Tell me a joke about programming"}
            ],
            "max_tokens": 50,
        },
    },
    {
        "custom_id": "request-2",
        "method": "POST",
        "url": "/chat/completions",
        "body": {
            "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
            "messages": [{"role": "user", "content": "What is Python?"}],
            "max_tokens": 50,
        },
    },
]

input_file_path = "batch_requests.jsonl"

with open(input_file_path, "w") as f:
    for req in requests:
        f.write(json.dumps(req) + "\n")

with open(input_file_path, "rb") as f:
    file_response = client.files.create(file=f, purpose="batch")

batch_response = client.batches.create(
    input_file_id=file_response.id,
    endpoint="/v1/chat/completions",
    completion_window="24h",
)

print_highlight(f"Batch job created with ID: {batch_response.id}")

[2025-04-13 23:26:12] INFO:     127.0.0.1:36102 - "POST /v1/files HTTP/1.1" 200 OK
[2025-04-13 23:26:12] INFO:     127.0.0.1:36102 - "POST /v1/batches HTTP/1.1" 200 OK

Batch job created with ID: batch_c33679c1-6205-4f51-87a8-650da8c42386

[2025-04-13 23:26:12 TP0] Prefill batch. #new-seq: 2, #new-token: 20, #cached-token: 60, token usage: 0.00, #running-req: 0, #queue-req: 0,

[8]:

while batch_response.status not in ["completed", "failed", "cancelled"]:
    time.sleep(3)
    print(f"Batch job status: {batch_response.status}...trying again in 3 seconds...")
    batch_response = client.batches.retrieve(batch_response.id)

if batch_response.status == "completed":
    print("Batch job completed successfully!")
    print(f"Request counts: {batch_response.request_counts}")

    result_file_id = batch_response.output_file_id
    file_response = client.files.content(result_file_id)
    result_content = file_response.read().decode("utf-8")

    results = [
        json.loads(line) for line in result_content.split("\n") if line.strip() != ""
    ]

    for result in results:
        print_highlight(f"Request {result['custom_id']}:")
        print_highlight(f"Response: {result['response']}")

    print_highlight("Cleaning up files...")
    # Only delete the result file ID since file_response is just content
    client.files.delete(result_file_id)
else:
    print_highlight(f"Batch job failed with status: {batch_response.status}")
    if hasattr(batch_response, "errors"):
        print_highlight(f"Errors: {batch_response.errors}")

[2025-04-13 23:26:13 TP0] Decode batch. #running-req: 1, #token: 62, token usage: 0.00, gen throughput (token/s): 57.59, #queue-req: 0,
Batch job status: validating...trying again in 3 seconds...
[2025-04-13 23:26:15] INFO:     127.0.0.1:36102 - "GET /v1/batches/batch_c33679c1-6205-4f51-87a8-650da8c42386 HTTP/1.1" 200 OK
Batch job completed successfully!
Request counts: BatchRequestCounts(completed=2, failed=0, total=2)
[2025-04-13 23:26:15] INFO:     127.0.0.1:36102 - "GET /v1/files/backend_result_file-fbaa89b3-db9a-4e12-b21e-eb3f137dceb9/content HTTP/1.1" 200 OK

Request request-1:

Response: {'status_code': 200, 'request_id': 'batch_c33679c1-6205-4f51-87a8-650da8c42386-req_0', 'body': {'id': 'batch_c33679c1-6205-4f51-87a8-650da8c42386-req_0', 'object': 'chat.completion', 'created': 1744586772, 'model': 'meta-llama/Meta-Llama-3.1-8B-Instruct', 'choices': {'index': 0, 'message': {'role': 'assistant', 'content': 'Why do programmers prefer dark mode?\n\nBecause light attracts bugs.', 'tool_calls': None, 'reasoning_content': None}, 'logprobs': None, 'finish_reason': 'stop', 'matched_stop': 128009}, 'usage': {'prompt_tokens': 41, 'completion_tokens': 13, 'total_tokens': 54}, 'system_fingerprint': None}}

Request request-2:

Response: {'status_code': 200, 'request_id': 'batch_c33679c1-6205-4f51-87a8-650da8c42386-req_1', 'body': {'id': 'batch_c33679c1-6205-4f51-87a8-650da8c42386-req_1', 'object': 'chat.completion', 'created': 1744586772, 'model': 'meta-llama/Meta-Llama-3.1-8B-Instruct', 'choices': {'index': 0, 'message': {'role': 'assistant', 'content': '**Python: A High-Level, Object-Oriented Programming Language**\n\nPython is a high-level, interpreted programming language that is widely used for various purposes such as web development, scientific computing, data analysis, artificial intelligence, and more. It was created', 'tool_calls': None, 'reasoning_content': None}, 'logprobs': None, 'finish_reason': 'length', 'matched_stop': None}, 'usage': {'prompt_tokens': 39, 'completion_tokens': 50, 'total_tokens': 89}, 'system_fingerprint': None}}

Cleaning up files...

[2025-04-13 23:26:15] INFO:     127.0.0.1:36102 - "DELETE /v1/files/backend_result_file-fbaa89b3-db9a-4e12-b21e-eb3f137dceb9 HTTP/1.1" 200 OK

It takes a while to complete the batch job. You can use these two APIs to retrieve the batch job status or cancel the batch job.

batches/{batch_id}: Retrieve the batch job status.
batches/{batch_id}/cancel: Cancel the batch job.

Here is an example to check the batch job status.

[9]:

import json
import time
from openai import OpenAI

client = OpenAI(base_url=f"http://127.0.0.1:{port}/v1", api_key="None")

requests = []
for i in range(20):
    requests.append(
        {
            "custom_id": f"request-{i}",
            "method": "POST",
            "url": "/chat/completions",
            "body": {
                "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
                "messages": [
                    {
                        "role": "system",
                        "content": f"{i}: You are a helpful AI assistant",
                    },
                    {
                        "role": "user",
                        "content": "Write a detailed story about topic. Make it very long.",
                    },
                ],
                "max_tokens": 64,
            },
        }
    )

input_file_path = "batch_requests.jsonl"
with open(input_file_path, "w") as f:
    for req in requests:
        f.write(json.dumps(req) + "\n")

with open(input_file_path, "rb") as f:
    uploaded_file = client.files.create(file=f, purpose="batch")

batch_job = client.batches.create(
    input_file_id=uploaded_file.id,
    endpoint="/v1/chat/completions",
    completion_window="24h",
)

print_highlight(f"Created batch job with ID: {batch_job.id}")
print_highlight(f"Initial status: {batch_job.status}")

time.sleep(10)

max_checks = 5
for i in range(max_checks):
    batch_details = client.batches.retrieve(batch_id=batch_job.id)

    print_highlight(
        f"Batch job details (check {i+1} / {max_checks}) // ID: {batch_details.id} // Status: {batch_details.status} // Created at: {batch_details.created_at} // Input file ID: {batch_details.input_file_id} // Output file ID: {batch_details.output_file_id}"
    )
    print_highlight(
        f"<strong>Request counts: Total: {batch_details.request_counts.total} // Completed: {batch_details.request_counts.completed} // Failed: {batch_details.request_counts.failed}</strong>"
    )

    time.sleep(3)

[2025-04-13 23:26:15] INFO:     127.0.0.1:36110 - "POST /v1/files HTTP/1.1" 200 OK
[2025-04-13 23:26:15] INFO:     127.0.0.1:36110 - "POST /v1/batches HTTP/1.1" 200 OK

Created batch job with ID: batch_a7fe5d02-a5a5-4baa-bece-60fc23622e41

Initial status: validating

[2025-04-13 23:26:16 TP0] Prefill batch. #new-seq: 12, #new-token: 360, #cached-token: 300, token usage: 0.00, #running-req: 0, #queue-req: 0,
[2025-04-13 23:26:16 TP0] Prefill batch. #new-seq: 8, #new-token: 240, #cached-token: 200, token usage: 0.02, #running-req: 12, #queue-req: 0,
[2025-04-13 23:26:16 TP0] Decode batch. #running-req: 20, #token: 885, token usage: 0.04, gen throughput (token/s): 93.64, #queue-req: 0,
[2025-04-13 23:26:16 TP0] Decode batch. #running-req: 20, #token: 1685, token usage: 0.08, gen throughput (token/s): 1708.65, #queue-req: 0,
[2025-04-13 23:26:26] INFO:     127.0.0.1:48990 - "GET /v1/batches/batch_a7fe5d02-a5a5-4baa-bece-60fc23622e41 HTTP/1.1" 200 OK

Batch job details (check 1 / 5) // ID: batch_a7fe5d02-a5a5-4baa-bece-60fc23622e41 // Status: completed // Created at: 1744586775 // Input file ID: backend_input_file-e1352d09-8ca6-4c95-85d8-56576ebcb9a2 // Output file ID: backend_result_file-a5bca005-c19f-40b3-a742-2c90035630a1