20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Fix profiling.py (#16202)

Browse Source 
Signed-off-by: zh Wang <rekind133@outlook.com>
This commit is contained in:
zh Wang 2025-04-10 01:03:34 +08:00 committed by GitHub
parent 098900d7c2
commit a25866ac8d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/offline_inference/profiling.py
View File

@ -234,9 +234,8 @@ def run_profile(context: ProfileContext, csv_output: Optional[str],
sampling_params.max_tokens = next(output_len_generator) sampling_params.max_tokens = next(output_len_generator)
assert isinstance(sampling_params.max_tokens, int) assert isinstance(sampling_params.max_tokens, int)
prompt_token_ids = torch.randint( prompt_token_ids = torch.randint(llm.get_tokenizer().vocab_size,
llm.llm_engine.model_config.get_vocab_size(), size=(prompt_len, )).tolist()
size=(prompt_len, )).tolist()
llm.llm_engine.add_request( llm.llm_engine.add_request(
request_id=f"seq{i}", request_id=f"seq{i}",