Change the name to vLLM (#150)

tests/kernels/test_activation.py

@@ -1,7 +1,7 @@
 import torch
 import torch.nn.functional as F
 
-from cacheflow import activation_ops
+from vllm import activation_ops
 
 
 def ref_silu_and_mul(x: torch.Tensor) -> torch.Tensor:

tests/kernels/test_attention.py

@@ -5,7 +5,7 @@ import torch
 from xformers import ops as xops
 from xformers.ops.fmha.attn_bias import BlockDiagonalCausalMask
 
-from cacheflow import attention_ops
+from vllm import attention_ops
 
 MAX_SEQ_LEN = 4096
 TEST_SEED = 0

tests/kernels/test_cache.py

@@ -2,7 +2,7 @@ import random
 
 import torch
 
-from cacheflow import cache_ops
+from vllm import cache_ops
 
 
 @torch.inference_mode()

tests/kernels/test_layernorm.py

@@ -1,7 +1,7 @@
 import torch
 import torch.nn as nn
 
-from cacheflow import layernorm_ops
+from vllm import layernorm_ops
 
 
 class RefRMSNorm(nn.Module):

tests/kernels/test_pos_encoding.py

@@ -4,7 +4,7 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
-from cacheflow import pos_encoding_ops
+from vllm import pos_encoding_ops
 
 
 def rotate_half(x: torch.Tensor) -> torch.Tensor: