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
67 lines
2.3 KiB
Python
67 lines
2.3 KiB
Python
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import Callable
|
|
from typing import Any, Optional
|
|
|
|
import torch
|
|
|
|
from sglang.jit_kernel.kv_canary.verify import CanaryLaunchTag
|
|
from sglang.srt.kv_canary.config import CanaryConfig
|
|
from sglang.srt.kv_canary.runner.future_tensor import DelayedDeviceHostHandler
|
|
from sglang.srt.kv_canary.runner.sweep import SweepOrchestrator
|
|
from sglang.srt.kv_canary.state import CanaryDeviceState
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class PeriodicCanaryStatsLogger:
|
|
def __init__(
|
|
self,
|
|
*,
|
|
config: CanaryConfig,
|
|
device_state: CanaryDeviceState,
|
|
active_tags: tuple[CanaryLaunchTag, ...],
|
|
outer_step_counter_getter: Callable[[], int],
|
|
sweep_orchestrator: SweepOrchestrator,
|
|
d2h_stream: torch.cuda.Stream,
|
|
) -> None:
|
|
self._config = config
|
|
self._device_state = device_state
|
|
self._active_tags = active_tags
|
|
self._outer_step_counter_getter = outer_step_counter_getter
|
|
self._sweep_orchestrator = sweep_orchestrator
|
|
self._handler = DelayedDeviceHostHandler(d2h_stream=d2h_stream)
|
|
|
|
def step(self) -> None:
|
|
self._handler.step(
|
|
compute_on_device=self._compute_on_device,
|
|
postprocess_on_host=self._postprocess_on_host,
|
|
)
|
|
|
|
def _compute_on_device(self) -> Optional[dict[str, Any]]:
|
|
period = self._config.stats_print_every_n_steps
|
|
if period <= 0:
|
|
return None
|
|
outer_step_counter = self._outer_step_counter_getter()
|
|
if outer_step_counter == 0 or outer_step_counter % period != 0:
|
|
return None
|
|
device_state = self._device_state
|
|
return {
|
|
"step": outer_step_counter,
|
|
"slot_sum": device_state.slot_run_counters.sum().view(1),
|
|
"write_index": device_state.violation_log.violation_write_index,
|
|
}
|
|
|
|
def _postprocess_on_host(self, host_data: dict[str, Any]) -> None:
|
|
logger.info(
|
|
"[canary] step=%d protected_tokens=%d sweep_passes=%d violations=%d "
|
|
"launch_tags_active=%d/%d",
|
|
int(host_data["step"]),
|
|
int(host_data["slot_sum"].item()),
|
|
self._sweep_orchestrator.sweep_passes,
|
|
int(host_data["write_index"].item()),
|
|
len(self._active_tags),
|
|
len(CanaryLaunchTag),
|
|
)
|