FastAPI service wrapping the Surya-OCR-2 model (datalab-to) served through vLLM: legacy /v1/api/ai/* endpoints, an OpenAI-compatible /v1/chat/completions endpoint, a coalescing request batcher, a local OCR CLI, Docker packaging, multilingual example outputs, and quantization/concurrency benchmarks. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
55 lines
14 KiB
JSON
55 lines
14 KiB
JSON
{
|
|
"started_at": "2026-06-10T12:01:21+0400",
|
|
"image": "/path/to/surya/static/images/excerpt.png",
|
|
"requests": 1,
|
|
"concurrency": 1,
|
|
"preflight": {
|
|
"docker_runtimes": {
|
|
"ok": true,
|
|
"stdout": "{\"io.containerd.runc.v2\":{\"path\":\"runc\",\"status\":{\"org.opencontainers.runtime-spec.features\":\"{\\\"ociVersionMin\\\":\\\"1.0.0\\\",\\\"ociVersionMax\\\":\\\"1.2.0\\\",\\\"hooks\\\":[\\\"prestart\\\",\\\"createRuntime\\\",\\\"createContainer\\\",\\\"startContainer\\\",\\\"poststart\\\",\\\"poststop\\\"],\\\"mountOptions\\\":[\\\"async\\\",\\\"atime\\\",\\\"bind\\\",\\\"defaults\\\",\\\"dev\\\",\\\"diratime\\\",\\\"dirsync\\\",\\\"exec\\\",\\\"iversion\\\",\\\"lazytime\\\",\\\"loud\\\",\\\"mand\\\",\\\"noatime\\\",\\\"nodev\\\",\\\"nodiratime\\\",\\\"noexec\\\",\\\"noiversion\\\",\\\"nolazytime\\\",\\\"nomand\\\",\\\"norelatime\\\",\\\"nostrictatime\\\",\\\"nosuid\\\",\\\"nosymfollow\\\",\\\"private\\\",\\\"ratime\\\",\\\"rbind\\\",\\\"rdev\\\",\\\"rdiratime\\\",\\\"relatime\\\",\\\"remount\\\",\\\"rexec\\\",\\\"rnoatime\\\",\\\"rnodev\\\",\\\"rnodiratime\\\",\\\"rnoexec\\\",\\\"rnorelatime\\\",\\\"rnostrictatime\\\",\\\"rnosuid\\\",\\\"rnosymfollow\\\",\\\"ro\\\",\\\"rprivate\\\",\\\"rrelatime\\\",\\\"rro\\\",\\\"rrw\\\",\\\"rshared\\\",\\\"rslave\\\",\\\"rstrictatime\\\",\\\"rsuid\\\",\\\"rsymfollow\\\",\\\"runbindable\\\",\\\"rw\\\",\\\"shared\\\",\\\"silent\\\",\\\"slave\\\",\\\"strictatime\\\",\\\"suid\\\",\\\"symfollow\\\",\\\"sync\\\",\\\"tmpcopyup\\\",\\\"unbindable\\\"],\\\"linux\\\":{\\\"namespaces\\\":[\\\"cgroup\\\",\\\"ipc\\\",\\\"mount\\\",\\\"network\\\",\\\"pid\\\",\\\"time\\\",\\\"user\\\",\\\"uts\\\"],\\\"capabilities\\\":[\\\"CAP_CHOWN\\\",\\\"CAP_DAC_OVERRIDE\\\",\\\"CAP_DAC_READ_SEARCH\\\",\\\"CAP_FOWNER\\\",\\\"CAP_FSETID\\\",\\\"CAP_KILL\\\",\\\"CAP_SETGID\\\",\\\"CAP_SETUID\\\",\\\"CAP_SETPCAP\\\",\\\"CAP_LINUX_IMMUTABLE\\\",\\\"CAP_NET_BIND_SERVICE\\\",\\\"CAP_NET_BROADCAST\\\",\\\"CAP_NET_ADMIN\\\",\\\"CAP_NET_RAW\\\",\\\"CAP_IPC_LOCK\\\",\\\"CAP_IPC_OWNER\\\",\\\"CAP_SYS_MODULE\\\",\\\"CAP_SYS_RAWIO\\\",\\\"CAP_SYS_CHROOT\\\",\\\"CAP_SYS_PTRACE\\\",\\\"CAP_SYS_PACCT\\\",\\\"CAP_SYS_ADMIN\\\",\\\"CAP_SYS_BOOT\\\",\\\"CAP_SYS_NICE\\\",\\\"CAP_SYS_RESOURCE\\\",\\\"CAP_SYS_TIME\\\",\\\"CAP_SYS_TTY_CONFIG\\\",\\\"CAP_MKNOD\\\",\\\"CAP_LEASE\\\",\\\"CAP_AUDIT_WRITE\\\",\\\"CAP_AUDIT_CONTROL\\\",\\\"CAP_SETFCAP\\\",\\\"CAP_MAC_OVERRIDE\\\",\\\"CAP_MAC_ADMIN\\\",\\\"CAP_SYSLOG\\\",\\\"CAP_WAKE_ALARM\\\",\\\"CAP_BLOCK_SUSPEND\\\",\\\"CAP_AUDIT_READ\\\",\\\"CAP_PERFMON\\\",\\\"CAP_BPF\\\",\\\"CAP_CHECKPOINT_RESTORE\\\"],\\\"cgroup\\\":{\\\"v1\\\":true,\\\"v2\\\":true,\\\"systemd\\\":true,\\\"systemdUser\\\":true,\\\"rdma\\\":true},\\\"seccomp\\\":{\\\"enabled\\\":true,\\\"actions\\\":[\\\"SCMP_ACT_ALLOW\\\",\\\"SCMP_ACT_ERRNO\\\",\\\"SCMP_ACT_KILL\\\",\\\"SCMP_ACT_KILL_PROCESS\\\",\\\"SCMP_ACT_KILL_THREAD\\\",\\\"SCMP_ACT_LOG\\\",\\\"SCMP_ACT_NOTIFY\\\",\\\"SCMP_ACT_TRACE\\\",\\\"SCMP_ACT_TRAP\\\"],\\\"operators\\\":[\\\"SCMP_CMP_EQ\\\",\\\"SCMP_CMP_GE\\\",\\\"SCMP_CMP_GT\\\",\\\"SCMP_CMP_LE\\\",\\\"SCMP_CMP_LT\\\",\\\"SCMP_CMP_MASKED_EQ\\\",\\\"SCMP_CMP_NE\\\"],\\\"archs\\\":[\\\"SCMP_ARCH_AARCH64\\\",\\\"SCMP_ARCH_ARM\\\",\\\"SCMP_ARCH_MIPS\\\",\\\"SCMP_ARCH_MIPS64\\\",\\\"SCMP_ARCH_MIPS64N32\\\",\\\"SCMP_ARCH_MIPSEL\\\",\\\"SCMP_ARCH_MIPSEL64\\\",\\\"SCMP_ARCH_MIPSEL64N32\\\",\\\"SCMP_ARCH_PPC\\\",\\\"SCMP_ARCH_PPC64\\\",\\\"SCMP_ARCH_PPC64LE\\\",\\\"SCMP_ARCH_RISCV64\\\",\\\"SCMP_ARCH_S390\\\",\\\"SCMP_ARCH_S390X\\\",\\\"SCMP_ARCH_X32\\\",\\\"SCMP_ARCH_X86\\\",\\\"SCMP_ARCH_X86_64\\\"],\\\"knownFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"],\\\"supportedFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"]},\\\"apparmor\\\":{\\\"enabled\\\":true},\\\"selinux\\\":{\\\"enabled\\\":true},\\\"intelRdt\\\":{\\\"enabled\\\":true},\\\"mountExtensions\\\":{\\\"idmap\\\":{\\\"enabled\\\":true}}},\\\"annotations\\\":{\\\"io.github.seccomp.libseccomp.version\\\":\\\"2.5.3\\\",\\\"org.opencontainers.runc.checkpoint.enabled\\\":\\\"true\\\",\\\"org.opencontainers.runc.commit\\\":\\\"v1.2.5-0-g59923ef\\\",\\\"org.opencontainers.runc.version\\\":\\\"1.2.5\\\"},\\\"potentiallyUnsafeConfigAnnotations\\\":[\\\"bundle\\\",\\\"org.systemd.property.\\\",\\\"org.criu.config\\\"]}\"}},\"nvidia\":{\"path\":\"nvidia-container-runtime\",\"status\":{\"org.opencontainers.runtime-spec.features\":\"{\\\"ociVersionMin\\\":\\\"1.0.0\\\",\\\"ociVersionMax\\\":\\\"1.2.0\\\",\\\"hooks\\\":[\\\"prestart\\\",\\\"createRuntime\\\",\\\"createContainer\\\",\\\"startContainer\\\",\\\"poststart\\\",\\\"poststop\\\"],\\\"mountOptions\\\":[\\\"async\\\",\\\"atime\\\",\\\"bind\\\",\\\"defaults\\\",\\\"dev\\\",\\\"diratime\\\",\\\"dirsync\\\",\\\"exec\\\",\\\"iversion\\\",\\\"lazytime\\\",\\\"loud\\\",\\\"mand\\\",\\\"noatime\\\",\\\"nodev\\\",\\\"nodiratime\\\",\\\"noexec\\\",\\\"noiversion\\\",\\\"nolazytime\\\",\\\"nomand\\\",\\\"norelatime\\\",\\\"nostrictatime\\\",\\\"nosuid\\\",\\\"nosymfollow\\\",\\\"private\\\",\\\"ratime\\\",\\\"rbind\\\",\\\"rdev\\\",\\\"rdiratime\\\",\\\"relatime\\\",\\\"remount\\\",\\\"rexec\\\",\\\"rnoatime\\\",\\\"rnodev\\\",\\\"rnodiratime\\\",\\\"rnoexec\\\",\\\"rnorelatime\\\",\\\"rnostrictatime\\\",\\\"rnosuid\\\",\\\"rnosymfollow\\\",\\\"ro\\\",\\\"rprivate\\\",\\\"rrelatime\\\",\\\"rro\\\",\\\"rrw\\\",\\\"rshared\\\",\\\"rslave\\\",\\\"rstrictatime\\\",\\\"rsuid\\\",\\\"rsymfollow\\\",\\\"runbindable\\\",\\\"rw\\\",\\\"shared\\\",\\\"silent\\\",\\\"slave\\\",\\\"strictatime\\\",\\\"suid\\\",\\\"symfollow\\\",\\\"sync\\\",\\\"tmpcopyup\\\",\\\"unbindable\\\"],\\\"linux\\\":{\\\"namespaces\\\":[\\\"cgroup\\\",\\\"ipc\\\",\\\"mount\\\",\\\"network\\\",\\\"pid\\\",\\\"time\\\",\\\"user\\\",\\\"uts\\\"],\\\"capabilities\\\":[\\\"CAP_CHOWN\\\",\\\"CAP_DAC_OVERRIDE\\\",\\\"CAP_DAC_READ_SEARCH\\\",\\\"CAP_FOWNER\\\",\\\"CAP_FSETID\\\",\\\"CAP_KILL\\\",\\\"CAP_SETGID\\\",\\\"CAP_SETUID\\\",\\\"CAP_SETPCAP\\\",\\\"CAP_LINUX_IMMUTABLE\\\",\\\"CAP_NET_BIND_SERVICE\\\",\\\"CAP_NET_BROADCAST\\\",\\\"CAP_NET_ADMIN\\\",\\\"CAP_NET_RAW\\\",\\\"CAP_IPC_LOCK\\\",\\\"CAP_IPC_OWNER\\\",\\\"CAP_SYS_MODULE\\\",\\\"CAP_SYS_RAWIO\\\",\\\"CAP_SYS_CHROOT\\\",\\\"CAP_SYS_PTRACE\\\",\\\"CAP_SYS_PACCT\\\",\\\"CAP_SYS_ADMIN\\\",\\\"CAP_SYS_BOOT\\\",\\\"CAP_SYS_NICE\\\",\\\"CAP_SYS_RESOURCE\\\",\\\"CAP_SYS_TIME\\\",\\\"CAP_SYS_TTY_CONFIG\\\",\\\"CAP_MKNOD\\\",\\\"CAP_LEASE\\\",\\\"CAP_AUDIT_WRITE\\\",\\\"CAP_AUDIT_CONTROL\\\",\\\"CAP_SETFCAP\\\",\\\"CAP_MAC_OVERRIDE\\\",\\\"CAP_MAC_ADMIN\\\",\\\"CAP_SYSLOG\\\",\\\"CAP_WAKE_ALARM\\\",\\\"CAP_BLOCK_SUSPEND\\\",\\\"CAP_AUDIT_READ\\\",\\\"CAP_PERFMON\\\",\\\"CAP_BPF\\\",\\\"CAP_CHECKPOINT_RESTORE\\\"],\\\"cgroup\\\":{\\\"v1\\\":true,\\\"v2\\\":true,\\\"systemd\\\":true,\\\"systemdUser\\\":true,\\\"rdma\\\":true},\\\"seccomp\\\":{\\\"enabled\\\":true,\\\"actions\\\":[\\\"SCMP_ACT_ALLOW\\\",\\\"SCMP_ACT_ERRNO\\\",\\\"SCMP_ACT_KILL\\\",\\\"SCMP_ACT_KILL_PROCESS\\\",\\\"SCMP_ACT_KILL_THREAD\\\",\\\"SCMP_ACT_LOG\\\",\\\"SCMP_ACT_NOTIFY\\\",\\\"SCMP_ACT_TRACE\\\",\\\"SCMP_ACT_TRAP\\\"],\\\"operators\\\":[\\\"SCMP_CMP_EQ\\\",\\\"SCMP_CMP_GE\\\",\\\"SCMP_CMP_GT\\\",\\\"SCMP_CMP_LE\\\",\\\"SCMP_CMP_LT\\\",\\\"SCMP_CMP_MASKED_EQ\\\",\\\"SCMP_CMP_NE\\\"],\\\"archs\\\":[\\\"SCMP_ARCH_AARCH64\\\",\\\"SCMP_ARCH_ARM\\\",\\\"SCMP_ARCH_MIPS\\\",\\\"SCMP_ARCH_MIPS64\\\",\\\"SCMP_ARCH_MIPS64N32\\\",\\\"SCMP_ARCH_MIPSEL\\\",\\\"SCMP_ARCH_MIPSEL64\\\",\\\"SCMP_ARCH_MIPSEL64N32\\\",\\\"SCMP_ARCH_PPC\\\",\\\"SCMP_ARCH_PPC64\\\",\\\"SCMP_ARCH_PPC64LE\\\",\\\"SCMP_ARCH_RISCV64\\\",\\\"SCMP_ARCH_S390\\\",\\\"SCMP_ARCH_S390X\\\",\\\"SCMP_ARCH_X32\\\",\\\"SCMP_ARCH_X86\\\",\\\"SCMP_ARCH_X86_64\\\"],\\\"knownFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"],\\\"supportedFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"]},\\\"apparmor\\\":{\\\"enabled\\\":true},\\\"selinux\\\":{\\\"enabled\\\":true},\\\"intelRdt\\\":{\\\"enabled\\\":true},\\\"mountExtensions\\\":{\\\"idmap\\\":{\\\"enabled\\\":true}}},\\\"annotations\\\":{\\\"io.github.seccomp.libseccomp.version\\\":\\\"2.5.3\\\",\\\"org.opencontainers.runc.checkpoint.enabled\\\":\\\"true\\\",\\\"org.opencontainers.runc.commit\\\":\\\"v1.2.5-0-g59923ef\\\",\\\"org.opencontainers.runc.version\\\":\\\"1.2.5\\\"},\\\"potentiallyUnsafeConfigAnnotations\\\":[\\\"bundle\\\",\\\"org.systemd.property.\\\",\\\"org.criu.config\\\"]}\"}},\"runc\":{\"path\":\"runc\",\"status\":{\"org.opencontainers.runtime-spec.features\":\"{\\\"ociVersionMin\\\":\\\"1.0.0\\\",\\\"ociVersionMax\\\":\\\"1.2.0\\\",\\\"hooks\\\":[\\\"prestart\\\",\\\"createRuntime\\\",\\\"createContainer\\\",\\\"startContainer\\\",\\\"poststart\\\",\\\"poststop\\\"],\\\"mountOptions\\\":[\\\"async\\\",\\\"atime\\\",\\\"bind\\\",\\\"defaults\\\",\\\"dev\\\",\\\"diratime\\\",\\\"dirsync\\\",\\\"exec\\\",\\\"iversion\\\",\\\"lazytime\\\",\\\"loud\\\",\\\"mand\\\",\\\"noatime\\\",\\\"nodev\\\",\\\"nodiratime\\\",\\\"noexec\\\",\\\"noiversion\\\",\\\"nolazytime\\\",\\\"nomand\\\",\\\"norelatime\\\",\\\"nostrictatime\\\",\\\"nosuid\\\",\\\"nosymfollow\\\",\\\"private\\\",\\\"ratime\\\",\\\"rbind\\\",\\\"rdev\\\",\\\"rdiratime\\\",\\\"relatime\\\",\\\"remount\\\",\\\"rexec\\\",\\\"rnoatime\\\",\\\"rnodev\\\",\\\"rnodiratime\\\",\\\"rnoexec\\\",\\\"rnorelatime\\\",\\\"rnostrictatime\\\",\\\"rnosuid\\\",\\\"rnosymfollow\\\",\\\"ro\\\",\\\"rprivate\\\",\\\"rrelatime\\\",\\\"rro\\\",\\\"rrw\\\",\\\"rshared\\\",\\\"rslave\\\",\\\"rstrictatime\\\",\\\"rsuid\\\",\\\"rsymfollow\\\",\\\"runbindable\\\",\\\"rw\\\",\\\"shared\\\",\\\"silent\\\",\\\"slave\\\",\\\"strictatime\\\",\\\"suid\\\",\\\"symfollow\\\",\\\"sync\\\",\\\"tmpcopyup\\\",\\\"unbindable\\\"],\\\"linux\\\":{\\\"namespaces\\\":[\\\"cgroup\\\",\\\"ipc\\\",\\\"mount\\\",\\\"network\\\",\\\"pid\\\",\\\"time\\\",\\\"user\\\",\\\"uts\\\"],\\\"capabilities\\\":[\\\"CAP_CHOWN\\\",\\\"CAP_DAC_OVERRIDE\\\",\\\"CAP_DAC_READ_SEARCH\\\",\\\"CAP_FOWNER\\\",\\\"CAP_FSETID\\\",\\\"CAP_KILL\\\",\\\"CAP_SETGID\\\",\\\"CAP_SETUID\\\",\\\"CAP_SETPCAP\\\",\\\"CAP_LINUX_IMMUTABLE\\\",\\\"CAP_NET_BIND_SERVICE\\\",\\\"CAP_NET_BROADCAST\\\",\\\"CAP_NET_ADMIN\\\",\\\"CAP_NET_RAW\\\",\\\"CAP_IPC_LOCK\\\",\\\"CAP_IPC_OWNER\\\",\\\"CAP_SYS_MODULE\\\",\\\"CAP_SYS_RAWIO\\\",\\\"CAP_SYS_CHROOT\\\",\\\"CAP_SYS_PTRACE\\\",\\\"CAP_SYS_PACCT\\\",\\\"CAP_SYS_ADMIN\\\",\\\"CAP_SYS_BOOT\\\",\\\"CAP_SYS_NICE\\\",\\\"CAP_SYS_RESOURCE\\\",\\\"CAP_SYS_TIME\\\",\\\"CAP_SYS_TTY_CONFIG\\\",\\\"CAP_MKNOD\\\",\\\"CAP_LEASE\\\",\\\"CAP_AUDIT_WRITE\\\",\\\"CAP_AUDIT_CONTROL\\\",\\\"CAP_SETFCAP\\\",\\\"CAP_MAC_OVERRIDE\\\",\\\"CAP_MAC_ADMIN\\\",\\\"CAP_SYSLOG\\\",\\\"CAP_WAKE_ALARM\\\",\\\"CAP_BLOCK_SUSPEND\\\",\\\"CAP_AUDIT_READ\\\",\\\"CAP_PERFMON\\\",\\\"CAP_BPF\\\",\\\"CAP_CHECKPOINT_RESTORE\\\"],\\\"cgroup\\\":{\\\"v1\\\":true,\\\"v2\\\":true,\\\"systemd\\\":true,\\\"systemdUser\\\":true,\\\"rdma\\\":true},\\\"seccomp\\\":{\\\"enabled\\\":true,\\\"actions\\\":[\\\"SCMP_ACT_ALLOW\\\",\\\"SCMP_ACT_ERRNO\\\",\\\"SCMP_ACT_KILL\\\",\\\"SCMP_ACT_KILL_PROCESS\\\",\\\"SCMP_ACT_KILL_THREAD\\\",\\\"SCMP_ACT_LOG\\\",\\\"SCMP_ACT_NOTIFY\\\",\\\"SCMP_ACT_TRACE\\\",\\\"SCMP_ACT_TRAP\\\"],\\\"operators\\\":[\\\"SCMP_CMP_EQ\\\",\\\"SCMP_CMP_GE\\\",\\\"SCMP_CMP_GT\\\",\\\"SCMP_CMP_LE\\\",\\\"SCMP_CMP_LT\\\",\\\"SCMP_CMP_MASKED_EQ\\\",\\\"SCMP_CMP_NE\\\"],\\\"archs\\\":[\\\"SCMP_ARCH_AARCH64\\\",\\\"SCMP_ARCH_ARM\\\",\\\"SCMP_ARCH_MIPS\\\",\\\"SCMP_ARCH_MIPS64\\\",\\\"SCMP_ARCH_MIPS64N32\\\",\\\"SCMP_ARCH_MIPSEL\\\",\\\"SCMP_ARCH_MIPSEL64\\\",\\\"SCMP_ARCH_MIPSEL64N32\\\",\\\"SCMP_ARCH_PPC\\\",\\\"SCMP_ARCH_PPC64\\\",\\\"SCMP_ARCH_PPC64LE\\\",\\\"SCMP_ARCH_RISCV64\\\",\\\"SCMP_ARCH_S390\\\",\\\"SCMP_ARCH_S390X\\\",\\\"SCMP_ARCH_X32\\\",\\\"SCMP_ARCH_X86\\\",\\\"SCMP_ARCH_X86_64\\\"],\\\"knownFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"],\\\"supportedFlags\\\":[\\\"SECCOMP_FILTER_FLAG_TSYNC\\\",\\\"SECCOMP_FILTER_FLAG_SPEC_ALLOW\\\",\\\"SECCOMP_FILTER_FLAG_LOG\\\"]},\\\"apparmor\\\":{\\\"enabled\\\":true},\\\"selinux\\\":{\\\"enabled\\\":true},\\\"intelRdt\\\":{\\\"enabled\\\":true},\\\"mountExtensions\\\":{\\\"idmap\\\":{\\\"enabled\\\":true}}},\\\"annotations\\\":{\\\"io.github.seccomp.libseccomp.version\\\":\\\"2.5.3\\\",\\\"org.opencontainers.runc.checkpoint.enabled\\\":\\\"true\\\",\\\"org.opencontainers.runc.commit\\\":\\\"v1.2.5-0-g59923ef\\\",\\\"org.opencontainers.runc.version\\\":\\\"1.2.5\\\"},\\\"potentiallyUnsafeConfigAnnotations\\\":[\\\"bundle\\\",\\\"org.systemd.property.\\\",\\\"org.criu.config\\\"]}\"}}}",
|
|
"stderr": ""
|
|
},
|
|
"nvidia_smi": {
|
|
"ok": true,
|
|
"stdout": "GPU 0: NVIDIA A100 80GB PCIe (UUID: GPU-911fab14-997f-e653-67c4-abba6d597ec6)\nGPU 1: NVIDIA A100 80GB PCIe (UUID: GPU-b6584aae-31c5-e793-7d22-98fbebef889f)\nGPU 2: NVIDIA A100 80GB PCIe (UUID: GPU-b72f3ad9-d411-a9da-c4a2-be9f0cb175fe)\nGPU 3: NVIDIA A100 80GB PCIe (UUID: GPU-e1d3ca84-f769-2e6d-4179-d3ec0ebd94f2)",
|
|
"stderr": ""
|
|
},
|
|
"nvidia_container_runtime": {
|
|
"ok": true,
|
|
"stdout": "/usr/bin/nvidia-container-runtime",
|
|
"stderr": ""
|
|
},
|
|
"nvidia_ctk": {
|
|
"ok": true,
|
|
"stdout": "/usr/bin/nvidia-ctk",
|
|
"stderr": ""
|
|
},
|
|
"docker_gpus": {
|
|
"ok": true,
|
|
"stdout": "GPU 0: NVIDIA A100 80GB PCIe (UUID: GPU-911fab14-997f-e653-67c4-abba6d597ec6)\nGPU 1: NVIDIA A100 80GB PCIe (UUID: GPU-b6584aae-31c5-e793-7d22-98fbebef889f)\nGPU 2: NVIDIA A100 80GB PCIe (UUID: GPU-b72f3ad9-d411-a9da-c4a2-be9f0cb175fe)\nGPU 3: NVIDIA A100 80GB PCIe (UUID: GPU-e1d3ca84-f769-2e6d-4179-d3ec0ebd94f2)",
|
|
"stderr": ""
|
|
},
|
|
"docker_has_nvidia_runtime": true,
|
|
"recommended_fix": "Run: sudo nvidia-ctk runtime configure --runtime=docker --config=/etc/docker/daemon.json && sudo systemctl restart docker"
|
|
},
|
|
"endpoints": [
|
|
{
|
|
"name": "vllm",
|
|
"url": "http://127.0.0.1:5002/v1/api/ai/suya_ocr_vllm/",
|
|
"requests": 1,
|
|
"concurrency": 1,
|
|
"success": 1,
|
|
"failed": 0,
|
|
"wall_seconds": 372.96746190078557,
|
|
"throughput_rps": 0.002681199037856052,
|
|
"latency_seconds": {
|
|
"min": 372.96655484382063,
|
|
"mean": 372.96655484382063,
|
|
"p50": 372.96655484382063,
|
|
"p95": 372.96655484382063,
|
|
"max": 372.96655484382063
|
|
},
|
|
"errors": []
|
|
}
|
|
]
|
|
} |