[Hardware] using current_platform.seed_everything (#9785)
Signed-off-by: wangshuai09 <391746016@qq.com>
This commit is contained in:
@@ -3,8 +3,8 @@ import time
|
||||
import torch
|
||||
|
||||
from vllm.model_executor.layers.layernorm import RMSNorm
|
||||
from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser,
|
||||
seed_everything)
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
|
||||
|
||||
|
||||
@torch.inference_mode()
|
||||
@@ -16,7 +16,7 @@ def main(num_tokens: int,
|
||||
do_profile: bool = False,
|
||||
num_warmup_iters: int = 5,
|
||||
num_iters: int = 100) -> None:
|
||||
seed_everything(seed)
|
||||
current_platform.seed_everything(seed)
|
||||
torch.set_default_device("cuda")
|
||||
|
||||
layer = RMSNorm(hidden_size).to(dtype=dtype)
|
||||
|
||||
@@ -10,7 +10,8 @@ from ray.experimental.tqdm_ray import tqdm
|
||||
from transformers import AutoConfig
|
||||
|
||||
from vllm.model_executor.layers.fused_moe.fused_moe import *
|
||||
from vllm.utils import FlexibleArgumentParser, seed_everything
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import FlexibleArgumentParser
|
||||
|
||||
|
||||
class BenchmarkConfig(TypedDict):
|
||||
@@ -167,7 +168,7 @@ class BenchmarkWorker:
|
||||
|
||||
def __init__(self, seed: int) -> None:
|
||||
torch.set_default_device("cuda")
|
||||
seed_everything(seed)
|
||||
current_platform.seed_everything(seed)
|
||||
self.seed = seed
|
||||
|
||||
def benchmark(
|
||||
@@ -181,7 +182,7 @@ class BenchmarkWorker:
|
||||
use_fp8_w8a8: bool,
|
||||
use_int8_w8a16: bool,
|
||||
) -> Tuple[Dict[str, int], float]:
|
||||
seed_everything(self.seed)
|
||||
current_platform.seed_everything(self.seed)
|
||||
dtype_str = get_config_dtype_str(dtype,
|
||||
use_int8_w8a16=use_int8_w8a16,
|
||||
use_fp8_w8a8=use_fp8_w8a8)
|
||||
|
||||
@@ -5,8 +5,9 @@ from typing import List, Optional
|
||||
import torch
|
||||
|
||||
from vllm import _custom_ops as ops
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser,
|
||||
create_kv_caches_with_random, seed_everything)
|
||||
create_kv_caches_with_random)
|
||||
|
||||
NUM_BLOCKS = 1024
|
||||
PARTITION_SIZE = 512
|
||||
@@ -28,7 +29,7 @@ def main(
|
||||
device: str = "cuda",
|
||||
kv_cache_dtype: Optional[str] = None,
|
||||
) -> None:
|
||||
seed_everything(seed)
|
||||
current_platform.seed_everything(seed)
|
||||
|
||||
scale = float(1.0 / (head_size**0.5))
|
||||
query = torch.empty(num_seqs,
|
||||
|
||||
@@ -3,8 +3,8 @@ import time
|
||||
import torch
|
||||
|
||||
from vllm import _custom_ops as ops
|
||||
from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser,
|
||||
seed_everything)
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, FlexibleArgumentParser
|
||||
|
||||
|
||||
@torch.inference_mode()
|
||||
@@ -17,7 +17,7 @@ def main(num_tokens: int,
|
||||
do_profile: bool = False,
|
||||
num_warmup_iters: int = 5,
|
||||
num_iters: int = 100) -> None:
|
||||
seed_everything(seed)
|
||||
current_platform.seed_everything(seed)
|
||||
torch.set_default_device("cuda")
|
||||
|
||||
x = torch.randn(num_tokens, hidden_size, dtype=dtype)
|
||||
|
||||
@@ -6,7 +6,8 @@ import torch
|
||||
|
||||
from vllm.model_executor.layers.rotary_embedding import (RotaryEmbedding,
|
||||
get_rope)
|
||||
from vllm.utils import FlexibleArgumentParser, seed_everything
|
||||
from vllm.platforms import current_platform
|
||||
from vllm.utils import FlexibleArgumentParser
|
||||
|
||||
|
||||
def benchmark_rope_kernels_multi_lora(
|
||||
@@ -22,7 +23,7 @@ def benchmark_rope_kernels_multi_lora(
|
||||
max_position: int = 8192,
|
||||
base: int = 10000,
|
||||
) -> None:
|
||||
seed_everything(seed)
|
||||
current_platform.seed_everything(seed)
|
||||
torch.set_default_device(device)
|
||||
if rotary_dim is None:
|
||||
rotary_dim = head_size
|
||||
|
||||
Reference in New Issue
Block a user