mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-21 10:15:53 +00:00
server-bench : add speed-bench for speculative decoding benchmarking (#23869)
* spec: add speed-bench support for benchmarking * speed-bench : add trailing newline to requirements.txt * speed-bench : bump datasets to 4.8.0 to fix ty check * server-bench : remove now-unused type: ignore after datasets bump
This commit is contained in:
@@ -25,7 +25,7 @@ def get_prompts_text(dataset_name: str, n_prompts: int) -> Optional[list[str]]:
|
||||
ret = []
|
||||
if dataset_name.lower() == "mmlu":
|
||||
logger.info("Loading MMLU dataset...")
|
||||
ret = datasets.load_dataset("cais/mmlu", "all")["test"]["question"] # type: ignore
|
||||
ret = datasets.load_dataset("cais/mmlu", "all")["test"]["question"]
|
||||
else:
|
||||
return None
|
||||
if n_prompts >= 0:
|
||||
|
||||
Reference in New Issue
Block a user