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

[CI/Build] Update Ruff version (#8469)

Browse Source 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Aaron Pham
2024-09-18 07:00:56 -04:00
committed by GitHub
parent 6ffa3f314c
commit 9d104b5beb
27 changed files with 50 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/test_cache_block_hashing.py
View File

@@ -66,8 +66,7 @@ def test_auto_prefix_caching(model: str, block_size: int, max_num_seqs: int,
hashes.append([])
prompts = [prefix + prompt for prompt in sample_prompts]
seq_id = 0
for prompt in prompts:
for seq_id, prompt in enumerate(prompts):
hashes[-1].append([])
prompt_token_ids = tokenizer.encode(prompt)
seq = Sequence(seq_id,
@@ -83,8 +82,6 @@ def test_auto_prefix_caching(model: str, block_size: int, max_num_seqs: int,
for idx in range(num_blocks):
hashes[-1][-1].append(seq.hash_of_block(idx))
seq_id += 1
# Check that hashes made with two prefixes with different first blocks are
# different everywhere.
for hash0, hash1 in zip(flatten_2d(hashes[0]), flatten_2d(hashes[1])):