Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
2.7 KiB
2.7 KiB
多GPU推理
某些模型现已支持内置的张量并行(Tensor Parallelism, TP),并通过 PyTorch 实现。张量并行技术将模型切分到多个 GPU 上,从而支持更大的模型尺寸,并对诸如矩阵乘法等计算任务进行并行化。
要启用张量并行,只需在调用 [~AutoModelForCausalLM.from_pretrained] 时传递参数 tp_plan="auto":
import os
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
# 初始化分布式环境
rank = int(os.environ["RANK"])
device = torch.device(f"cuda:{rank}")
torch.cuda.set_device(device)
torch.distributed.init_process_group("nccl", device_id=device)
# 获取支持张量并行的模型
model = AutoModelForCausalLM.from_pretrained(
model_id,
tp_plan="auto",
)
# 准备输入tokens
tokenizer = AutoTokenizer.from_pretrained(model_id)
prompt = "Can I help"
inputs = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
# 分布式运行
outputs = model(inputs)
您可以使用 torchrun 命令启动上述脚本,多进程模式会自动将每个进程映射到一张 GPU:
torchrun --nproc-per-node 4 demo.py
目前,PyTorch 张量并行支持以下模型:
如果您希望对其他模型添加张量并行支持,可以通过提交 GitHub Issue 或 Pull Request 来提出请求。
预期性能提升
对于推理场景(尤其是处理大批量或长序列的输入),张量并行可以显著提升计算速度。
以下是 Llama 模型在序列长度为 512 且不同批量大小情况下的单次前向推理的预期加速效果:
