fix(plugin): gate dual-stream MoE by runtime graph mode

[wuhuikx]

Problem

In vLLM plugin mode, CUDA/HIP graph capture is owned by vLLM and the concrete runtime mode is selected per forward (FULL, PIECEWISE, or NONE). ATOM's MoE dispatcher instead checked its static compilation config.

For FULL_AND_PIECEWISE, the plugin maps vLLM's compile mode to ATOM level 3, which initializes the ATOM-side static graph mode as PIECEWISE. As a result, decode forwards that vLLM actually dispatches as FULL are incorrectly forced onto the single-stream MoE path. This was observed while validating Kimi-K3 dual-stream shared/routed expert overlap in #1752.

Solution

• Resolve the concrete graph mode from the active frontend's forward context.
• Normalize frontend enums by name instead of relying on matching numeric values.
• Fall back to ATOM's native forward context when vLLM context is unavailable.
• Disable dual-stream MoE only for an actual PIECEWISE forward; preserve it for eager/NONE and whole-model FULL capture.
• Add focused tests for enum translation, frontend fallback, runtime dispatch, token threshold, TBO, and the existing _use_dual_stream gate.

Validation

• python -m pytest -q tests/test_module_dispatch_ops.py tests/plugin/test_plugin_config_translation.py tests/plugin/test_vllm_kimi_k3.py — 22 passed
• Kimi-K3 TP8 with vLLM FULL_DECODE_ONLY and FULL_AND_PIECEWISE
• Profiler confirmed decode dual-stream graph execution on all TP ranks; with the native-matched online quant configuration, measured stream overlap was 99.1%–100%

Made with Cursor

[github-actions]

🏷️ CI Guide

Runs automatically on every eligible PR before approval:

• ✅ Pre Checkin: Black, Ruff, catalog schema validation, non-GPU unit tests

Heavy model tests:

• ✅ Run after the PR is approved and Pre Checkin passes
• ✅ Run immediately when an approval review is submitted
• ✅ Can be requested before approval with labels

Label	Tests
ci:full	Run all heavy PR model tests: native ATOM, vLLM, and SGLang
ci:atom	Run native ATOM model accuracy tests
ci:vllm	Run ATOM vLLM OOT model accuracy tests
ci:sglang	Run ATOM SGLang model accuracy tests

Heavy jobs are skipped when the PR is not approved and no matching ci:* label is present.
Add labels via the sidebar or gh pr edit 1790 --add-label <label>

[github-actions]

⚠️ [ruff] <I001> _{reported by reviewdog 🐶}
Import block is un-sorted or un-formatted

ATOM/atom/utils/forward_context.py

Lines 4 to 14 in 0c66975

	import logging
	import threading
	from contextlib import contextmanager
	from dataclasses import dataclass, field, fields
	from enum import Enum
	from typing import Any, Union
	import numpy as np
	import torch
	from atom.config import CUDAGraphMode, Config, KVCacheTensor, ParallelConfig

[wuhuikx]

Closing to resubmit the change from @XiaobingSuper.