biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert formatting to use ruff instead of yapf + isort (#26247)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-10-05 15:06:22 +01:00
committed by GitHub
parent 17edd8a807
commit d6953beb91
1508 changed files with 115244 additions and 94146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/kernels/attention/test_triton_decode_attention.py
View File

@@ -24,14 +24,12 @@ def test_decode_attention(B, L, H_Q, H_KV, D_QK, D_V, CACHE_SIZE, PAGE_SIZE):
num_kv_splits = 8
num_pages_per_batch = cdiv(seq_len, PAGE_SIZE)
req_to_page = torch.randint(0,
CACHE_SIZE // PAGE_SIZE,
(B, num_pages_per_batch, 1),
device="cuda")
req_to_page = torch.randint(
0, CACHE_SIZE // PAGE_SIZE, (B, num_pages_per_batch, 1), device="cuda"
)
req_to_token = req_to_page * PAGE_SIZE
req_to_token = req_to_token.expand(B, num_pages_per_batch, PAGE_SIZE)
req_to_token = req_to_token + torch.arange(PAGE_SIZE, device="cuda").view(
1, 1, -1)
req_to_token = req_to_token + torch.arange(PAGE_SIZE, device="cuda").view(1, 1, -1)
req_to_token = req_to_token.view(B, -1)
req_to_token = req_to_token[:, :seq_len].contiguous()
@@ -48,7 +46,7 @@ def test_decode_attention(B, L, H_Q, H_KV, D_QK, D_V, CACHE_SIZE, PAGE_SIZE):
lse = torch.zeros(B, H_Q, dtype=dtype, device="cuda")
b_seq_len = torch.full((B, ), seq_len, device="cuda")
b_seq_len = torch.full((B,), seq_len, device="cuda")
attn_logits = torch.empty(
(B, H_Q, num_kv_splits, D_V + 1),