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
86 lines
2.9 KiB
Python
86 lines
2.9 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
# Adapted from https://github.com/vllm-project/vllm/blob/v0.10.0/vllm/compilation/fx_utils.py
|
|
|
|
import operator
|
|
from collections.abc import Iterable, Iterator
|
|
from typing import Optional
|
|
|
|
from torch import fx
|
|
from torch._higher_order_ops.auto_functionalize import auto_functionalized
|
|
from torch._ops import OpOverload
|
|
|
|
|
|
def is_func(node: fx.Node, target) -> bool:
|
|
return node.op == "call_function" and node.target == target
|
|
|
|
|
|
def is_auto_func(node: fx.Node, op: OpOverload) -> bool:
|
|
return is_func(node, auto_functionalized) and node.args[0] == op
|
|
|
|
|
|
# Returns the first specified node with the given op (if it exists)
|
|
def find_specified_fn_maybe(
|
|
nodes: Iterable[fx.Node], op: OpOverload
|
|
) -> Optional[fx.Node]:
|
|
for node in nodes:
|
|
if node.target == op:
|
|
return node
|
|
return None
|
|
|
|
|
|
# Returns the first specified node with the given op
|
|
def find_specified_fn(nodes: Iterable[fx.Node], op: OpOverload) -> fx.Node:
|
|
node = find_specified_fn_maybe(nodes, op)
|
|
assert node is not None, f"Could not find {op} in nodes {nodes}"
|
|
return node
|
|
|
|
|
|
# Returns the first auto_functionalized node with the given op (if it exists)
|
|
def find_auto_fn_maybe(nodes: Iterable[fx.Node], op: OpOverload) -> Optional[fx.Node]:
|
|
for node in nodes:
|
|
if is_func(node, auto_functionalized) and node.args[0] == op: # noqa
|
|
return node
|
|
return None
|
|
|
|
|
|
# Returns the first auto_functionalized node with the given op
|
|
def find_auto_fn(nodes: Iterable[fx.Node], op: OpOverload) -> fx.Node:
|
|
node = find_auto_fn_maybe(nodes, op)
|
|
assert node is not None, f"Could not find {op} in nodes {nodes}"
|
|
return node
|
|
|
|
|
|
# Returns the getitem node that extracts the idx-th element from node
|
|
# (if it exists)
|
|
def find_getitem_maybe(node: fx.Node, idx: int) -> Optional[fx.Node]:
|
|
for user in node.users:
|
|
if is_func(user, operator.getitem) and user.args[1] == idx:
|
|
return user
|
|
return None
|
|
|
|
|
|
# Returns the getitem node that extracts the idx-th element from node
|
|
def find_getitem(node: fx.Node, idx: int) -> fx.Node:
|
|
ret = find_getitem_maybe(node, idx)
|
|
assert ret is not None, f"Could not find getitem {idx} in node {node}"
|
|
return ret
|
|
|
|
|
|
# An auto-functionalization-aware utility for finding nodes with a specific op
|
|
def find_op_nodes(op: OpOverload, graph: fx.Graph) -> Iterator[fx.Node]:
|
|
if not op._schema.is_mutable:
|
|
yield from graph.find_nodes(op="call_function", target=op)
|
|
|
|
for n in graph.find_nodes(op="call_function", target=auto_functionalized):
|
|
if n.args[0] == op:
|
|
yield n
|
|
|
|
|
|
# Asserts that the node only has one user and returns it
|
|
# Even if a node has only 1 user, it might share storage with another node,
|
|
# which might need to be taken into account.
|
|
def get_only_user(node: fx.Node) -> fx.Node:
|
|
assert len(node.users) == 1
|
|
return next(iter(node.users))
|