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
78 lines
2.0 KiB
Python
78 lines
2.0 KiB
Python
"""Context-manager wrappers around sglang.srt.observability.trace for diffusion tracing.
|
|
|
|
All tracing helpers for the multimodal_gen subsystem are consolidated here so
|
|
that call sites can use simple ``with`` statements instead of manual
|
|
start/end bookkeeping.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from contextlib import contextmanager
|
|
from dataclasses import dataclass
|
|
|
|
DIFFUSION_TRACE_MODULE = "diffusion"
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class DiffStageConfig:
|
|
"""A named trace stage with a default nesting level."""
|
|
|
|
stage_name: str
|
|
level: int = 0
|
|
|
|
|
|
class DiffStage:
|
|
"""Named trace stages for the diffusion pipeline."""
|
|
|
|
SCHEDULER_DISPATCH = DiffStageConfig("scheduler_dispatch", level=1)
|
|
GPU_FORWARD = DiffStageConfig("gpu_forward", level=2)
|
|
|
|
|
|
def init_diffusion_tracing(server_args, thread_label: str):
|
|
if not server_args.enable_trace:
|
|
return
|
|
|
|
from sglang.srt.observability.trace import (
|
|
process_tracing_init,
|
|
trace_set_thread_info,
|
|
)
|
|
|
|
# srt owns TraceReqContext and filters spans through its trace_modules list
|
|
process_tracing_init(
|
|
server_args.otlp_traces_endpoint,
|
|
"sglang-diffusion",
|
|
trace_modules=DIFFUSION_TRACE_MODULE,
|
|
)
|
|
trace_set_thread_info(thread_label)
|
|
|
|
|
|
@contextmanager
|
|
def trace_req(trace_ctx):
|
|
"""Ensure ``trace_req_finish()`` is called when a request scope exits.
|
|
|
|
Usage::
|
|
|
|
with trace_req(batch.trace_ctx):
|
|
...
|
|
"""
|
|
try:
|
|
yield trace_ctx
|
|
finally:
|
|
trace_ctx.trace_req_finish()
|
|
|
|
|
|
@contextmanager
|
|
def trace_slice(trace_ctx, stage: DiffStageConfig, **kwargs):
|
|
"""Context manager for a single trace slice (span).
|
|
|
|
Usage::
|
|
|
|
with trace_slice(req.trace_ctx, DiffStage.GPU_FORWARD):
|
|
result = pipeline.forward(req, server_args)
|
|
"""
|
|
trace_ctx.trace_slice_start(stage.stage_name, level=stage.level)
|
|
try:
|
|
yield trace_ctx
|
|
finally:
|
|
trace_ctx.trace_slice_end(stage.stage_name, level=stage.level, **kwargs)
|