xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-20 07:45:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

check input length of sonnet samples (#16423)

Browse Source 
Signed-off-by: alexey-belyakov <alexey.belyakov@intel.com>
This commit is contained in:
Alexey Belyakov 2025-04-11 03:15:06 +01:00 committed by GitHub
parent 268c325078
commit 3e397a9484
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
benchmarks/benchmark_dataset.py
View File

@ -489,7 +489,7 @@ class SonnetDataset(BenchmarkDataset):
prefix_lines = self.data[:num_prefix_lines] prefix_lines = self.data[:num_prefix_lines]
samples = [] samples = []
for _ in range(num_requests): while len(samples) < num_requests:
extra_lines = random.choices(self.data, extra_lines = random.choices(self.data,
k=num_input_lines - num_prefix_lines) k=num_input_lines - num_prefix_lines)
prompt = f"{base_prompt}{''.join(prefix_lines + extra_lines)}" prompt = f"{base_prompt}{''.join(prefix_lines + extra_lines)}"
@ -497,6 +497,7 @@ class SonnetDataset(BenchmarkDataset):
prompt_formatted = tokenizer.apply_chat_template( prompt_formatted = tokenizer.apply_chat_template(
msg, add_generation_prompt=True, tokenize=False) msg, add_generation_prompt=True, tokenize=False)
prompt_len = len(tokenizer(prompt_formatted).input_ids) prompt_len = len(tokenizer(prompt_formatted).input_ids)
if prompt_len <= input_len:
samples.append( samples.append(
SampleRequest( SampleRequest(
prompt=prompt_formatted prompt=prompt_formatted