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
77 lines
2.6 KiB
Python
77 lines
2.6 KiB
Python
"""Gauge with gt/le bucket labels for Grafana heatmap visualization.
|
|
|
|
Unlike Prometheus Histogram which uses cumulative buckets, this uses
|
|
non-cumulative buckets (gt < value <= le) suitable for heatmap display.
|
|
|
|
Note: Keep in sync with Rust implementation in
|
|
sgl-model-gateway/src/observability/gauge_histogram.rs
|
|
"""
|
|
|
|
import bisect
|
|
from typing import Dict, Iterator, List, Tuple, Union
|
|
|
|
|
|
class BucketLabels:
|
|
"""Bucket label pairs and count computation for a GaugeHistogram."""
|
|
|
|
def __init__(self, upper_bounds: List[Union[int, float]]):
|
|
self._upper_bounds = upper_bounds
|
|
self._labels: List[Tuple[str, str]] = []
|
|
for i, upper in enumerate(upper_bounds):
|
|
lower = upper_bounds[i - 1] if i > 0 else 0
|
|
self._labels.append((str(lower), str(upper)))
|
|
self._labels.append((str(upper_bounds[-1]), "+Inf"))
|
|
|
|
def __len__(self) -> int:
|
|
return len(self._labels)
|
|
|
|
def __iter__(self) -> Iterator[Tuple[str, str]]:
|
|
return iter(self._labels)
|
|
|
|
def compute_bucket_counts(self, observations: List[Union[int, float]]) -> List[int]:
|
|
"""Compute how many observations fall into each bucket. O(n) complexity."""
|
|
counts = [0] * len(self)
|
|
for v in observations:
|
|
# bisect_left finds insertion point; values at boundary go to current bucket
|
|
idx = bisect.bisect_left(self._upper_bounds, v)
|
|
counts[idx] += 1
|
|
return counts
|
|
|
|
|
|
class GaugeHistogram:
|
|
"""Gauge with gt/le bucket labels for Grafana heatmap visualization."""
|
|
|
|
def __init__(
|
|
self,
|
|
name: str,
|
|
documentation: str,
|
|
labelnames: List[str],
|
|
bucket_bounds: List[Union[int, float]],
|
|
multiprocess_mode: str = "mostrecent",
|
|
):
|
|
from prometheus_client import Gauge
|
|
|
|
self._buckets = BucketLabels(bucket_bounds)
|
|
|
|
self._gauge = Gauge(
|
|
name=name,
|
|
documentation=documentation,
|
|
labelnames=list(labelnames) + ["gt", "le"],
|
|
multiprocess_mode=multiprocess_mode,
|
|
)
|
|
|
|
def set_raw(self, labels: Dict[str, str], values: List[int]):
|
|
"""Set bucket counts directly."""
|
|
for (gt, le), count in zip(self._buckets, values):
|
|
self._gauge.labels(**labels, gt=gt, le=le).set(count)
|
|
|
|
def set_by_current_observations(
|
|
self, labels: Dict[str, str], observations: List[Union[int, float]]
|
|
):
|
|
"""Compute bucket counts from observations and set them."""
|
|
counts = self._buckets.compute_bucket_counts(observations)
|
|
self.set_raw(labels, counts)
|
|
|
|
def buckets(self) -> BucketLabels:
|
|
return self._buckets
|