项目文件夹

文件
wehub-resource-sync 94057c3d3e
PR Test (NPU) / check-changes (push) Has been cancelled
PR Test (NPU) / pr-gate (push) Has been cancelled
PR Test (NPU) / set-image-config (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-1-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (0) (push) Has been cancelled
PR Test (NPU) / stage-b-test-2-npu-a2 (1) (push) Has been cancelled
PR Test (NPU) / stage-b-test-4-npu-a3 (push) Has been cancelled
PR Test (NPU) / stage-b-test-16-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-1-npu-a3 (push) Has been cancelled
PR Test (NPU) / multimodal-gen-test-2-npu-a3 (push) Has been cancelled
PR Test (Arm64) / pr-gate (push) Has been cancelled
PR Test (Arm64) / check-changes (push) Has been cancelled
PR Test (Arm64) / build-test (push) Has been cancelled
PR Test (sgl-router) / gate (push) Has been cancelled
PR Test (sgl-router) / tier-1 — lint (push) Has been cancelled
PR Test (sgl-router) / tier-2 — build + test (push) Has been cancelled
PR Test (sgl-router) / tier-3 — docker (placeholder) (push) Has been cancelled
PR Test (sgl-router) / tier-3 — k8s integration (push) Has been cancelled
PR Test (sgl-router) / tier-3 — e2e (push) Has been cancelled
PR Test (sgl-router) / finish (push) Has been cancelled
PR Test (NPU) / single-node-poc (map[name:qwen3_6_27b_w8a8_1p_in64k_out1k_50ms runner:linux-aarch64-a3-2 test_case:test/registered/ascend/performance/qwen3_6_27b/test_npu_qwen3_6_27b_w8a8_1p_in64k_out1k_50ms.py test_type:perf]) (push) Has been cancelled
PR Test (NPU) / pr-test-npu-finish (push) Has been cancelled
PR Test (Xeon) / pr-gate (push) Has been cancelled
PR Test (Xeon) / check-changes (push) Has been cancelled
PR Test (Xeon) / build-test (, xeon-gnr, base-b-test-cpu) (push) Has been cancelled
PR Test (XPU) / check-changes (push) Has been cancelled
PR Test (XPU) / pr-gate (push) Has been cancelled
PR Test (XPU) / stage-a-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / wait-for-stage-a (push) Has been cancelled
PR Test (XPU) / stage-b-test-1-gpu-xpu (push) Has been cancelled
PR Test (XPU) / finish (push) Has been cancelled
CI Model Inventory / build-inventory (push) Has been cancelled
Lint / lint (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Compilation Check (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Manual Policy (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark - Request Processing (push) Has been cancelled
PR Benchmark (SMG Components) / Benchmark Summary (push) Has been cancelled
PR Test (SMG) / build-wheel (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on windows (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (x86_64 - auto) (push) Has been cancelled
PR Test (SMG) / python-unit-tests (push) Has been cancelled
PR Test (SMG) / unit-tests (push) Has been cancelled
PR Test (SMG) / benchmarks (push) Has been cancelled
PR Test (SMG) / chat-completions (push) Has been cancelled
PR Test (SMG) / chat-completions-4gpu (push) Has been cancelled
PR Test (SMG) / e2e (push) Has been cancelled
PR Test (SMG) / docker-build-test (push) Has been cancelled
PR Test (SMG) / k8s-integration (push) Has been cancelled
PR Test (SMG) / finish (push) Has been cancelled
PR Test (SMG) / summarize-benchmarks (push) Has been cancelled
Release SGLang Model Gateway Docker Image / publish (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on macos (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - auto) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (aarch64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / build on linux (x86_64 - musllinux_1_1) (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Build SDist (push) Has been cancelled
Release SGLang Model Gateway to PyPI / Upload to PyPI (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (aarch64, 12.9, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu129-matrix (x86_64, 12.9, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu129 (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (aarch64, 13.0, 3.10, arm-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / build-cu130-matrix (x86_64, 13.0, 3.10, x64-kernel-build-node) (push) Has been cancelled
Release SGLang Kernels / release-cu130 (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 700) (push) Has been cancelled
Release SGLang Kernels / build-rocm-matrix (3.10, 720) (push) Has been cancelled
Release SGLang Kernels / release-rocm700 (push) Has been cancelled
Release SGLang Kernels / release-rocm720 (push) Has been cancelled
Release SGLang Kernels / build-musa43 (43, 3.10) (push) Has been cancelled
Release SGLang Kernels / release-musa43 (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:38:16 +08:00

221 行
6.2 KiB
Rust

use serde_json::json;
use crate::common::{
mock_worker::{HealthStatus, MockWorkerConfig, WorkerType},
WorkerTestContext,
};
#[cfg(test)]
mod tests {
use super::*;
#[tokio::test]
async fn test_generate_streaming() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20001,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 10,
fail_rate: 0.0,
}])
.await;
let payload = json!({
"text": "Stream test",
"stream": true,
"sampling_params": {
"temperature": 0.7,
"max_new_tokens": 10
}
});
let result = ctx.make_streaming_request("/generate", payload).await;
assert!(result.is_ok());
let events = result.unwrap();
assert!(events.len() >= 2);
assert_eq!(events.last().unwrap(), "[DONE]");
ctx.shutdown().await;
}
#[tokio::test]
async fn test_v1_chat_completions_streaming() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20002,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 10,
fail_rate: 0.0,
}])
.await;
let payload = json!({
"model": "test-model",
"messages": [
{"role": "user", "content": "Count to 3"}
],
"stream": true,
"max_tokens": 20
});
let result = ctx
.make_streaming_request("/v1/chat/completions", payload)
.await;
assert!(result.is_ok());
let events = result.unwrap();
assert!(events.len() >= 2);
for event in &events {
if event != "[DONE]" {
let parsed: Result<serde_json::Value, _> = serde_json::from_str(event);
assert!(parsed.is_ok(), "Invalid JSON in SSE event: {}", event);
let json = parsed.unwrap();
assert_eq!(
json.get("object").and_then(|v| v.as_str()),
Some("chat.completion.chunk")
);
}
}
ctx.shutdown().await;
}
#[tokio::test]
async fn test_v1_completions_streaming() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20003,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 10,
fail_rate: 0.0,
}])
.await;
let payload = json!({
"model": "test-model",
"prompt": "Once upon a time",
"stream": true,
"max_tokens": 15
});
let result = ctx.make_streaming_request("/v1/completions", payload).await;
assert!(result.is_ok());
let events = result.unwrap();
assert!(events.len() >= 2);
ctx.shutdown().await;
}
#[tokio::test]
async fn test_streaming_with_error() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20004,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 0,
fail_rate: 1.0,
}])
.await;
let payload = json!({
"text": "This should fail",
"stream": true
});
let result = ctx.make_streaming_request("/generate", payload).await;
assert!(result.is_err());
ctx.shutdown().await;
}
#[tokio::test]
async fn test_streaming_timeouts() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20005,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 100,
fail_rate: 0.0,
}])
.await;
let payload = json!({
"text": "Slow stream",
"stream": true,
"sampling_params": {
"max_new_tokens": 5
}
});
let start = std::time::Instant::now();
let result = ctx.make_streaming_request("/generate", payload).await;
let elapsed = start.elapsed();
assert!(result.is_ok());
let events = result.unwrap();
assert!(!events.is_empty());
assert!(elapsed.as_millis() >= 100);
ctx.shutdown().await;
}
#[tokio::test]
async fn test_batch_streaming() {
let ctx = WorkerTestContext::new(vec![MockWorkerConfig {
port: 20006,
worker_type: WorkerType::Regular,
health_status: HealthStatus::Healthy,
response_delay_ms: 10,
fail_rate: 0.0,
}])
.await;
let payload = json!({
"text": ["First", "Second", "Third"],
"stream": true,
"sampling_params": {
"max_new_tokens": 5
}
});
let result = ctx.make_streaming_request("/generate", payload).await;
assert!(result.is_ok());
let events = result.unwrap();
assert!(events.len() >= 4);
ctx.shutdown().await;
}
#[tokio::test]
async fn test_sse_format_parsing() {
let parse_sse_chunk = |chunk: &[u8]| -> Vec<String> {
let text = String::from_utf8_lossy(chunk);
text.lines()
.filter(|line| line.starts_with("data: "))
.map(|line| line[6..].to_string())
.collect()
};
let sse_data =
b"data: {\"text\":\"Hello\"}\n\ndata: {\"text\":\" world\"}\n\ndata: [DONE]\n\n";
let events = parse_sse_chunk(sse_data);
assert_eq!(events.len(), 3);
assert_eq!(events[0], "{\"text\":\"Hello\"}");
assert_eq!(events[1], "{\"text\":\" world\"}");
assert_eq!(events[2], "[DONE]");
let mixed = b"event: message\ndata: {\"test\":true}\n\n: comment\ndata: [DONE]\n\n";
let events = parse_sse_chunk(mixed);
assert_eq!(events.len(), 2);
assert_eq!(events[0], "{\"test\":true}");
assert_eq!(events[1], "[DONE]");
}
}