Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Bug]: 使用vllm+lmcache部署glm4.7，在多并发+长上下文导致服务挂掉 [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
vllm-project/vllm#37680•Fetched 2026-04-08 01:04:05
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
feichenchinafeichenchina
Participants
feichenchinafeichenchina
Timeline (top)
labeled ×1

Error Message

import asyncio import aiohttp import time import os import statistics

================= 基本配置 =================

BASE_URL = "http://localhost:17000/v1" MODEL = "GLM-4.7-FP8"

API_KEY = os.getenv( "OPENAI_API_KEY", "sk-NL13poi1SG6FRnVzaW9u7GJHMntKL7rN" )

⚠️ 长上下文 + LMCache，强烈建议从 1 并发开始

CONCURRENCY = int(os.getenv("CONCURRENCY", "5")) TOTAL_REQUESTS = int(os.getenv("TOTAL_REQUESTS", "3000"))

MAX_TOKENS = int(os.getenv("MAX_TOKENS", "256")) TEMPERATURE = 0.2

================= 构造 ≈ 60k token 输入 =================

说明：

- 使用中文短句，避免 tokenizer 过度压缩

- REPEAT_TIMES 明显放大，宁可超过，不要不足

BASE_SENTENCE = f"这是用于超长上下文和KV缓存压力测试的标准测试句子。{time.time()}" REPEAT_TIMES = int(os.getenv("REPEAT_TIMES", "4500")) # 控制在 128k token 上限内并保留生成余量

LONG_PROMPT = ( "请完整、逐字处理以下长文本，不要跳过、不要总结中间内容。\n\n" + BASE_SENTENCE * REPEAT_TIMES + "\n\n问题：请用一句话说明上述文本的主要用途。" )

print(f"[INFO] Prompt 字符长度 ≈ {len(LONG_PROMPT):,}")

================= 单请求 =================

async def send_request(session, idx, latencies, results, errors): url = f"{BASE_URL}/chat/completions" headers = { "Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json", }

payload = {
    "model": MODEL,
    "messages": [
        {"role": "user", "content": LONG_PROMPT}
    ],
    "max_tokens": MAX_TOKENS,
    "temperature": TEMPERATURE,
    "stream": False
}

start = time.perf_counter()
try:
    async with session.post(
        url,
        json=payload,
        headers=headers,
        timeout=aiohttp.ClientTimeout(total=1200)
    ) as resp:

        # ✅ HTTP 失败：只记失败，不记成功
        if resp.status != 200:
            errors.append(f"HTTP {resp.status}")
            return

        data = await resp.json()
        latency = time.perf_counter() - start

        # ✅ 只有完整成功才记录 latency / result
        latencies.append(latency)

        reply = data["choices"][0]["message"]["content"]
        results.append(reply)

        print(f"\n========== 请求 {idx} 返回 ==========")
        print(reply[:500])  # 防止刷屏
        print("========== 结束 ==========\n")

except Exception as e:
    # ✅ 异常请求：只记失败
    errors.append(str(e))

================= 压测主逻辑 =================

async def run_load_test(): connector = aiohttp.TCPConnector(limit=CONCURRENCY) timeout = aiohttp.ClientTimeout(total=1800)

latencies = []
results = []
errors = []

start_time = time.time()

async with aiohttp.ClientSession(
    connector=connector,
    timeout=timeout
) as session:

    tasks = []
    for i in range(TOTAL_REQUESTS):
        tasks.append(send_request(session, i, latencies, results, errors))
        if len(tasks) >= CONCURRENCY:
            await asyncio.gather(*tasks)
            tasks = []
    if tasks:
        await asyncio.gather(*tasks)

total_time = time.time() - start_time

# ================= 统计（已修正） =================
print("\n========== 压测统计 ==========")
print(f"总请求数:     {TOTAL_REQUESTS}")
print(f"成功请求数:   {len(latencies)}")
print(f"失败请求数:   {len(errors)}")
print(f"总耗时:       {total_time:.2f} s")

if latencies:
    avg = statistics.mean(latencies)
    print(f"平均延迟:     {avg:.2f} s")

    # ✅ 小样本不算“伪 P95”
    if len(latencies) >= 20:
        p95 = statistics.quantiles(latencies, n=20)[18]
        print(f"P95 延迟:     {p95:.2f} s")
    else:
        print(f"P95 延迟:     N/A（样本不足）")

    qps = len(latencies) / total_time
    print(f"QPS:          {qps:.3f}")

if errors:
    print("\n错误示例（最多 3 条）:")
    for e in errors[:3]:
        print(" -", e)

if name == "main": asyncio.run(run_load_test())

Fix Action

Fix / Workaround

============================== CPU Info

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 192 On-line CPU(s) list: 0-191 Vendor ID: GenuineIntel BIOS Vendor ID: Intel(R) Corporation Model name: Intel(R) Xeon(R) Platinum 8468 BIOS Model name: Intel(R) Xeon(R) Platinum 8468 CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 48 Socket(s): 2 Stepping: 8 BogoMIPS: 4200.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves xfd cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 4.5 MiB (96 instances) L1i cache: 3 MiB (96 instances) L2 cache: 192 MiB (96 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-47,96-143 NUMA node1 CPU(s): 48-95,144-191 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS, IBPB conditional, PBRSB-eIBRS SW sequence Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Code Example

import asyncio
import aiohttp
import time
import os
import statistics

# ================= 基本配置 =================
BASE_URL = "http://localhost:17000/v1"
MODEL = "GLM-4.7-FP8"

API_KEY = os.getenv(
    "OPENAI_API_KEY",
    "sk-NL13poi1SG6FRnVzaW9u7GJHMntKL7rN"
)

# ⚠️ 长上下文 + LMCache，强烈建议从 1 并发开始
CONCURRENCY = int(os.getenv("CONCURRENCY", "5"))
TOTAL_REQUESTS = int(os.getenv("TOTAL_REQUESTS", "3000"))

MAX_TOKENS = int(os.getenv("MAX_TOKENS", "256"))
TEMPERATURE = 0.2

# ================= 构造 ≈ 60k token 输入 =================
# 说明：
# - 使用中文短句，避免 tokenizer 过度压缩
# - REPEAT_TIMES 明显放大，宁可超过，不要不足
BASE_SENTENCE = f"这是用于超长上下文和KV缓存压力测试的标准测试句子。{time.time()}"
REPEAT_TIMES = int(os.getenv("REPEAT_TIMES", "4500"))  # 控制在 128k token 上限内并保留生成余量

LONG_PROMPT = (
    "请完整、逐字处理以下长文本，不要跳过、不要总结中间内容。\n\n"
    + BASE_SENTENCE * REPEAT_TIMES +
    "\n\n问题：请用一句话说明上述文本的主要用途。"
)

print(f"[INFO] Prompt 字符长度 ≈ {len(LONG_PROMPT):,}")

# ================= 单请求 =================
async def send_request(session, idx, latencies, results, errors):
    url = f"{BASE_URL}/chat/completions"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    }

    payload = {
        "model": MODEL,
        "messages": [
            {"role": "user", "content": LONG_PROMPT}
        ],
        "max_tokens": MAX_TOKENS,
        "temperature": TEMPERATURE,
        "stream": False
    }

    start = time.perf_counter()
    try:
        async with session.post(
            url,
            json=payload,
            headers=headers,
            timeout=aiohttp.ClientTimeout(total=1200)
        ) as resp:

            # ✅ HTTP 失败：只记失败，不记成功
            if resp.status != 200:
                errors.append(f"HTTP {resp.status}")
                return

            data = await resp.json()
            latency = time.perf_counter() - start

            # ✅ 只有完整成功才记录 latency / result
            latencies.append(latency)

            reply = data["choices"][0]["message"]["content"]
            results.append(reply)

            print(f"\n========== 请求 {idx} 返回 ==========")
            print(reply[:500])  # 防止刷屏
            print("========== 结束 ==========\n")

    except Exception as e:
        # ✅ 异常请求：只记失败
        errors.append(str(e))


# ================= 压测主逻辑 =================
async def run_load_test():
    connector = aiohttp.TCPConnector(limit=CONCURRENCY)
    timeout = aiohttp.ClientTimeout(total=1800)

    latencies = []
    results = []
    errors = []

    start_time = time.time()

    async with aiohttp.ClientSession(
        connector=connector,
        timeout=timeout
    ) as session:

        tasks = []
        for i in range(TOTAL_REQUESTS):
            tasks.append(send_request(session, i, latencies, results, errors))
            if len(tasks) >= CONCURRENCY:
                await asyncio.gather(*tasks)
                tasks = []
        if tasks:
            await asyncio.gather(*tasks)

    total_time = time.time() - start_time

    # ================= 统计（已修正） =================
    print("\n========== 压测统计 ==========")
    print(f"总请求数:     {TOTAL_REQUESTS}")
    print(f"成功请求数:   {len(latencies)}")
    print(f"失败请求数:   {len(errors)}")
    print(f"总耗时:       {total_time:.2f} s")

    if latencies:
        avg = statistics.mean(latencies)
        print(f"平均延迟:     {avg:.2f} s")

        # ✅ 小样本不算“伪 P95”
        if len(latencies) >= 20:
            p95 = statistics.quantiles(latencies, n=20)[18]
            print(f"P95 延迟:     {p95:.2f} s")
        else:
            print(f"P95 延迟:     N/A（样本不足）")

        qps = len(latencies) / total_time
        print(f"QPS:          {qps:.3f}")

    if errors:
        print("\n错误示例（最多 3 条）:")
        for e in errors[:3]:
            print(" -", e)


if __name__ == "__main__":
    asyncio.run(run_load_test())
RAW_BUFFERClick to expand / collapse

Your current environment

Collecting environment information...

    System Info

============================== OS : Ubuntu 22.04.5 LTS (x86_64) GCC version : (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0 Clang version : Could not collect CMake version : Could not collect Libc version : glibc-2.35

============================== PyTorch Info

PyTorch version : 2.9.1+cu129 Is debug build : False CUDA used to build PyTorch : 12.9 ROCM used to build PyTorch : N/A

============================== Python Environment

Python version : 3.12.12 (main, Oct 10 2025, 08:52:57) [GCC 11.4.0] (64-bit runtime) Python platform : Linux-5.10.0-291.0.0.194.u187.fos23.x86_64-x86_64-with-glibc2.35

============================== CUDA / GPU Info

Is CUDA available : True CUDA runtime version : 12.9.86 CUDA_MODULE_LOADING set to : GPU models and configuration : GPU 0: NVIDIA H20 GPU 1: NVIDIA H20 GPU 2: NVIDIA H20 GPU 3: NVIDIA H20 GPU 4: NVIDIA H20 GPU 5: NVIDIA H20 GPU 6: NVIDIA H20 GPU 7: NVIDIA H20

Nvidia driver version : 550.163.01 cuDNN version : Could not collect HIP runtime version : N/A MIOpen runtime version : N/A Is XNNPACK available : True

============================== CPU Info

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 192 On-line CPU(s) list: 0-191 Vendor ID: GenuineIntel BIOS Vendor ID: Intel(R) Corporation Model name: Intel(R) Xeon(R) Platinum 8468 BIOS Model name: Intel(R) Xeon(R) Platinum 8468 CPU family: 6 Model: 143 Thread(s) per core: 2 Core(s) per socket: 48 Socket(s): 2 Stepping: 8 BogoMIPS: 4200.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves xfd cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 4.5 MiB (96 instances) L1i cache: 3 MiB (96 instances) L2 cache: 192 MiB (96 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-47,96-143 NUMA node1 CPU(s): 48-95,144-191 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS, IBPB conditional, PBRSB-eIBRS SW sequence Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

============================== Versions of relevant libraries

[pip3] flashinfer-python==0.6.1 [pip3] numpy==2.2.6 [pip3] nvidia-cublas-cu12==12.9.1.4 [pip3] nvidia-cuda-cupti-cu12==12.9.79 [pip3] nvidia-cuda-nvrtc-cu12==12.9.86 [pip3] nvidia-cuda-runtime-cu12==12.9.79 [pip3] nvidia-cudnn-cu12==9.10.2.21 [pip3] nvidia-cudnn-frontend==1.18.0 [pip3] nvidia-cufft-cu12==11.4.1.4 [pip3] nvidia-cufile-cu12==1.14.1.1 [pip3] nvidia-curand-cu12==10.3.10.19 [pip3] nvidia-cusolver-cu12==11.7.5.82 [pip3] nvidia-cusparse-cu12==12.5.10.65 [pip3] nvidia-cusparselt-cu12==0.7.1 [pip3] nvidia-cutlass-dsl==4.3.5 [pip3] nvidia-ml-py==13.590.48 [pip3] nvidia-nccl-cu12==2.27.5 [pip3] nvidia-nvjitlink-cu12==12.9.86 [pip3] nvidia-nvshmem-cu12==3.3.20 [pip3] nvidia-nvtx-cu12==12.9.79 [pip3] pyzmq==27.1.0 [pip3] torch==2.9.1+cu129 [pip3] torchaudio==2.9.1+cu129 [pip3] torchvision==0.24.1+cu129 [pip3] transformers==4.57.6 [pip3] triton==3.5.1 [conda] Could not collect

============================== vLLM Info

ROCM Version : Could not collect vLLM Version : 0.15.1 vLLM Build Flags: CUDA Archs: 7.0 7.5 8.0 8.9 9.0 10.0 12.0; ROCm: Disabled GPU Topology: GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE NODE NODE PIX NODE NODE SYS SYS SYS SYS 0-47,96-143 0 N/A GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE NODE NODE PIX NODE SYS SYS SYS SYS 0-47,96-143 0 N/A GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE NODE NODE PIX SYS SYS SYS SYS 0-47,96-143 0 N/A GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS SYS SYS PIX NODE NODE NODE 48-95,144-191 1 N/A GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS SYS SYS NODE PIX NODE NODE 48-95,144-191 1 N/A GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS SYS SYS NODE NODE PIX NODE 48-95,144-191 1 N/A GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS SYS SYS NODE NODE NODE PIX 48-95,144-191 1 N/A NIC0 PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE NODE NODE SYS SYS SYS SYS NIC1 NODE NODE NODE NODE SYS SYS SYS SYS NODE X PIX NODE NODE NODE SYS SYS SYS SYS NIC2 NODE NODE NODE NODE SYS SYS SYS SYS NODE PIX X NODE NODE NODE SYS SYS SYS SYS NIC3 NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE SYS SYS SYS SYS NIC4 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE SYS SYS SYS SYS NIC5 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE NODE NODE X SYS SYS SYS SYS NIC6 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS X NODE NODE NODE NIC7 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS NODE X NODE NODE NIC8 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS NODE NODE X NODE NIC9 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS NODE NODE NODE X

Legend:

X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks

NIC Legend:

NIC0: mlx5_0 NIC1: mlx5_1 NIC2: mlx5_2 NIC3: mlx5_3 NIC4: mlx5_4 NIC5: mlx5_5 NIC6: mlx5_6 NIC7: mlx5_7 NIC8: mlx5_8 NIC9: mlx5_9

============================== Environment Variables

NVIDIA_VISIBLE_DEVICES=all NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 brand=unknown,driver>=570,driver<571 brand=grid,driver>=570,driver<571 brand=tesla,driver>=570,driver<571 brand=nvidia,driver>=570,driver<571 brand=quadro,driver>=570,driver<571 brand=quadrortx,driver>=570,driver<571 brand=nvidiartx,driver>=570,driver<571 brand=vapps,driver>=570,driver<571 brand=vpc,driver>=570,driver<571 brand=vcs,driver>=570,driver<571 brand=vws,driver>=570,driver<571 brand=cloudgaming,driver>=570,driver<571 TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.9 9.0 10.0 12.0 NVIDIA_DRIVER_CAPABILITIES=compute,utility VLLM_USAGE_SOURCE=production-docker-image CUDA_VERSION=12.9.1 LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib64 PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1

🐛 Describe the bug

复现步骤：启动服务后，启动该脚本，执行一半将该脚本对应进程杀死，同时立即再次执行该脚本

import asyncio
import aiohttp
import time
import os
import statistics

# ================= 基本配置 =================
BASE_URL = "http://localhost:17000/v1"
MODEL = "GLM-4.7-FP8"

API_KEY = os.getenv(
    "OPENAI_API_KEY",
    "sk-NL13poi1SG6FRnVzaW9u7GJHMntKL7rN"
)

# ⚠️ 长上下文 + LMCache，强烈建议从 1 并发开始
CONCURRENCY = int(os.getenv("CONCURRENCY", "5"))
TOTAL_REQUESTS = int(os.getenv("TOTAL_REQUESTS", "3000"))

MAX_TOKENS = int(os.getenv("MAX_TOKENS", "256"))
TEMPERATURE = 0.2

# ================= 构造 ≈ 60k token 输入 =================
# 说明：
# - 使用中文短句，避免 tokenizer 过度压缩
# - REPEAT_TIMES 明显放大，宁可超过，不要不足
BASE_SENTENCE = f"这是用于超长上下文和KV缓存压力测试的标准测试句子。{time.time()}"
REPEAT_TIMES = int(os.getenv("REPEAT_TIMES", "4500"))  # 控制在 128k token 上限内并保留生成余量

LONG_PROMPT = (
    "请完整、逐字处理以下长文本，不要跳过、不要总结中间内容。\n\n"
    + BASE_SENTENCE * REPEAT_TIMES +
    "\n\n问题：请用一句话说明上述文本的主要用途。"
)

print(f"[INFO] Prompt 字符长度 ≈ {len(LONG_PROMPT):,}")

# ================= 单请求 =================
async def send_request(session, idx, latencies, results, errors):
    url = f"{BASE_URL}/chat/completions"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    }

    payload = {
        "model": MODEL,
        "messages": [
            {"role": "user", "content": LONG_PROMPT}
        ],
        "max_tokens": MAX_TOKENS,
        "temperature": TEMPERATURE,
        "stream": False
    }

    start = time.perf_counter()
    try:
        async with session.post(
            url,
            json=payload,
            headers=headers,
            timeout=aiohttp.ClientTimeout(total=1200)
        ) as resp:

            # ✅ HTTP 失败：只记失败，不记成功
            if resp.status != 200:
                errors.append(f"HTTP {resp.status}")
                return

            data = await resp.json()
            latency = time.perf_counter() - start

            # ✅ 只有完整成功才记录 latency / result
            latencies.append(latency)

            reply = data["choices"][0]["message"]["content"]
            results.append(reply)

            print(f"\n========== 请求 {idx} 返回 ==========")
            print(reply[:500])  # 防止刷屏
            print("========== 结束 ==========\n")

    except Exception as e:
        # ✅ 异常请求：只记失败
        errors.append(str(e))


# ================= 压测主逻辑 =================
async def run_load_test():
    connector = aiohttp.TCPConnector(limit=CONCURRENCY)
    timeout = aiohttp.ClientTimeout(total=1800)

    latencies = []
    results = []
    errors = []

    start_time = time.time()

    async with aiohttp.ClientSession(
        connector=connector,
        timeout=timeout
    ) as session:

        tasks = []
        for i in range(TOTAL_REQUESTS):
            tasks.append(send_request(session, i, latencies, results, errors))
            if len(tasks) >= CONCURRENCY:
                await asyncio.gather(*tasks)
                tasks = []
        if tasks:
            await asyncio.gather(*tasks)

    total_time = time.time() - start_time

    # ================= 统计（已修正） =================
    print("\n========== 压测统计 ==========")
    print(f"总请求数:     {TOTAL_REQUESTS}")
    print(f"成功请求数:   {len(latencies)}")
    print(f"失败请求数:   {len(errors)}")
    print(f"总耗时:       {total_time:.2f} s")

    if latencies:
        avg = statistics.mean(latencies)
        print(f"平均延迟:     {avg:.2f} s")

        # ✅ 小样本不算“伪 P95”
        if len(latencies) >= 20:
            p95 = statistics.quantiles(latencies, n=20)[18]
            print(f"P95 延迟:     {p95:.2f} s")
        else:
            print(f"P95 延迟:     N/A（样本不足）")

        qps = len(latencies) / total_time
        print(f"QPS:          {qps:.3f}")

    if errors:
        print("\n错误示例（最多 3 条）:")
        for e in errors[:3]:
            print(" -", e)


if __name__ == "__main__":
    asyncio.run(run_load_test())

报错信息：https://gist.github.com/feichenchina/02d904f6e02249991faea85509cdcc2a

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

Fix Plan

The issue seems to be related to the load test script. To fix this, we need to modify the script to handle exceptions and errors properly.

Here are the steps to fix the issue:

  • Modify the send_request function to handle exceptions and errors.
  • Add a retry mechanism to handle temporary failures.
  • Limit the number of concurrent requests to prevent overloading the server.

Code Changes

import asyncio
import aiohttp
import time
import os
import statistics

# ... (other code remains the same)

async def send_request(session, idx, latencies, results, errors):
    url = f"{BASE_URL}/chat/completions"
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json",
    }

    payload = {
        "model": MODEL,
        "messages": [
            {"role": "user", "content": LONG_PROMPT}
        ],
        "max_tokens": MAX_TOKENS,
        "temperature": TEMPERATURE,
        "stream": False
    }

    start = time.perf_counter()
    retry_count = 0
    max_retries = 3

    while retry_count < max_retries:
        try:
            async with session.post(
                url,
                json=payload,
                headers=headers,
                timeout=aiohttp.ClientTimeout(total=1200)
            ) as resp:

                # ✅ HTTP 失败：只记失败，不记成功
                if resp.status != 200:
                    errors.append(f"HTTP {resp.status}")
                    return

                data = await resp.json()
                latency = time.perf_counter() - start

                # ✅ 只有完整成功才记录 latency / result
                latencies.append(latency)

                reply = data["choices"][0]["message"]["content"]
                results.append(reply)

                print(f"\n========== 请求 {idx} 返回 ==========")
                print(reply[:500])  # 防止刷屏
                print("========== 结束 ==========\n")

                break

        except Exception as e:
            # ✅ 异常请求：只记失败
            errors.append(str(e))
            retry_count += 1
            await asyncio.sleep(1)  # wait for 1 second before retrying

    if retry_count == max_retries:
        errors.append("Max retries exceeded")

# ... (other code remains the same)

async def run_load_test():
    connector = aiohttp.TCPConnector(limit=CONCURRENCY)
    timeout = aiohttp.ClientTimeout(total=1800)

    latencies = []
    results = []
    errors = []

    start_time = time.time()

    async with aiohttp.ClientSession(
        connector=connector,
        timeout=timeout
    ) as session:

        tasks = []
        for i in range(TOTAL_REQUESTS):
            tasks.append(send

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#optimization#mixed precision#training loop#environment variable

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING