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
114 lines
3.2 KiB
Python
114 lines
3.2 KiB
Python
import pickle
|
|
import time
|
|
from pathlib import Path
|
|
from typing import Any, List, Optional
|
|
|
|
import pybase64
|
|
import torch
|
|
|
|
from sglang.srt.utils import MultiprocessingSerializer
|
|
|
|
|
|
class NaiveDistributed:
|
|
def __init__(self, rank: int, world_size: int, rendezvous: str):
|
|
self._rank = rank
|
|
self._world_size = world_size
|
|
self._operation_index = 0
|
|
self._directory = Path(rendezvous)
|
|
self._directory.mkdir(parents=True, exist_ok=True)
|
|
assert 0 <= rank < world_size
|
|
|
|
# both barrier to be safe, and as a sanity check
|
|
self.barrier()
|
|
|
|
def get_rank(self):
|
|
return self._rank
|
|
|
|
def get_world_size(self):
|
|
return self._world_size
|
|
|
|
def scatter(
|
|
self, tensor: torch.Tensor, scatter_list: List[torch.Tensor], src: int = 0
|
|
):
|
|
if self._rank == src:
|
|
assert len(scatter_list) == self._world_size
|
|
else:
|
|
assert scatter_list is None
|
|
|
|
gathered_objects = self.all_gather_object(
|
|
dict(
|
|
serialized_scatter_list=[
|
|
(
|
|
None
|
|
if item_rank == src
|
|
else MultiprocessingSerializer.serialize(item)
|
|
)
|
|
for item_rank, item in enumerate(scatter_list)
|
|
]
|
|
)
|
|
if self._rank == src
|
|
else dict()
|
|
)
|
|
|
|
remote_serialized_tensor = gathered_objects[src]["serialized_scatter_list"][
|
|
self._rank
|
|
]
|
|
if self._rank == src:
|
|
assert remote_serialized_tensor is None
|
|
remote_tensor = scatter_list[self._rank]
|
|
else:
|
|
remote_tensor = MultiprocessingSerializer.deserialize(
|
|
remote_serialized_tensor
|
|
)
|
|
tensor.copy_(remote_tensor)
|
|
|
|
# avoid src tensor be deleted too early
|
|
self.barrier()
|
|
|
|
def all_gather_object(self, obj: Any) -> List[Any]:
|
|
self._operation_index += 1
|
|
|
|
text_postfix = "\n"
|
|
|
|
def _get_path(interesting_rank: int):
|
|
return (
|
|
self._directory
|
|
/ f"rank{interesting_rank}_op{self._operation_index}.txt"
|
|
)
|
|
|
|
_get_path(self._rank).write_text(
|
|
pybase64.b64encode(pickle.dumps(obj)).decode("utf-8") + text_postfix
|
|
)
|
|
|
|
def _read_one(interesting_rank: int):
|
|
p = _get_path(interesting_rank)
|
|
while True:
|
|
if p.exists() and (text := p.read_text()).endswith(text_postfix):
|
|
return pickle.loads(
|
|
pybase64.b64decode(text[: -len(text_postfix)], validate=True)
|
|
)
|
|
time.sleep(0.001)
|
|
|
|
return [
|
|
_read_one(interesting_rank) for interesting_rank in range(self._world_size)
|
|
]
|
|
|
|
def barrier(self):
|
|
actual_objs = self.all_gather_object(self._rank)
|
|
assert actual_objs == list(range(self._world_size)), f"{actual_objs=}"
|
|
|
|
|
|
# Can have multi instances if needed
|
|
_instance: Optional[NaiveDistributed] = None
|
|
|
|
|
|
def get_naive_distributed():
|
|
assert _instance is not None
|
|
return _instance
|
|
|
|
|
|
def set_naive_distributed(instance: NaiveDistributed):
|
|
global _instance
|
|
assert _instance is None
|
|
_instance = instance
|