Deprecate best_of Sampling Parameter in anticipation for vLLM V1 (#13997)
Signed-off-by: vincent-4 <vincentzhongy+githubvincent4@gmail.com> Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
co-authored by
Brayden Zhong
Harry Mellor
parent
a32c8669ca
commit
a4f1ee35d6
@@ -27,7 +27,6 @@ class RequestFuncInput:
|
||||
output_len: int
|
||||
model: str
|
||||
model_name: Optional[str] = None
|
||||
best_of: int = 1
|
||||
logprobs: Optional[int] = None
|
||||
extra_body: Optional[dict] = None
|
||||
multi_modal_content: Optional[dict] = None
|
||||
@@ -58,7 +57,6 @@ async def async_request_tgi(
|
||||
async with aiohttp.ClientSession(trust_env=True,
|
||||
timeout=AIOHTTP_TIMEOUT) as session:
|
||||
params = {
|
||||
"best_of": request_func_input.best_of,
|
||||
"max_new_tokens": request_func_input.output_len,
|
||||
"do_sample": True,
|
||||
"temperature": 0.01, # TGI does not accept 0.0 temperature.
|
||||
@@ -130,7 +128,6 @@ async def async_request_trt_llm(
|
||||
|
||||
async with aiohttp.ClientSession(trust_env=True,
|
||||
timeout=AIOHTTP_TIMEOUT) as session:
|
||||
assert request_func_input.best_of == 1
|
||||
payload = {
|
||||
"accumulate_tokens": True,
|
||||
"text_input": request_func_input.prompt,
|
||||
@@ -195,7 +192,6 @@ async def async_request_deepspeed_mii(
|
||||
) -> RequestFuncOutput:
|
||||
async with aiohttp.ClientSession(trust_env=True,
|
||||
timeout=AIOHTTP_TIMEOUT) as session:
|
||||
assert request_func_input.best_of == 1
|
||||
|
||||
payload = {
|
||||
"prompt": request_func_input.prompt,
|
||||
@@ -249,7 +245,6 @@ async def async_request_openai_completions(
|
||||
if request_func_input.model_name else request_func_input.model,
|
||||
"prompt": request_func_input.prompt,
|
||||
"temperature": 0.0,
|
||||
"best_of": request_func_input.best_of,
|
||||
"max_tokens": request_func_input.output_len,
|
||||
"logprobs": request_func_input.logprobs,
|
||||
"stream": True,
|
||||
|
||||
@@ -560,7 +560,6 @@ async def benchmark(
|
||||
tokenizer: PreTrainedTokenizerBase,
|
||||
input_requests: list[tuple[str, int, int]],
|
||||
logprobs: Optional[int],
|
||||
best_of: int,
|
||||
request_rate: float,
|
||||
burstiness: float,
|
||||
disable_tqdm: bool,
|
||||
@@ -592,7 +591,6 @@ async def benchmark(
|
||||
prompt_len=test_prompt_len,
|
||||
output_len=test_output_len,
|
||||
logprobs=logprobs,
|
||||
best_of=best_of,
|
||||
multi_modal_content=test_mm_content,
|
||||
ignore_eos=ignore_eos,
|
||||
)
|
||||
@@ -619,7 +617,6 @@ async def benchmark(
|
||||
prompt_len=test_prompt_len,
|
||||
output_len=test_output_len,
|
||||
logprobs=logprobs,
|
||||
best_of=best_of,
|
||||
multi_modal_content=test_mm_content,
|
||||
ignore_eos=ignore_eos)
|
||||
profile_output = await request_func(request_func_input=profile_input)
|
||||
@@ -668,7 +665,6 @@ async def benchmark(
|
||||
prompt_len=prompt_len,
|
||||
output_len=output_len,
|
||||
logprobs=logprobs,
|
||||
best_of=best_of,
|
||||
multi_modal_content=mm_content,
|
||||
ignore_eos=ignore_eos)
|
||||
tasks.append(
|
||||
@@ -686,7 +682,6 @@ async def benchmark(
|
||||
prompt_len=test_prompt_len,
|
||||
output_len=test_output_len,
|
||||
logprobs=logprobs,
|
||||
best_of=best_of,
|
||||
)
|
||||
profile_output = await request_func(request_func_input=profile_input)
|
||||
if profile_output.success:
|
||||
@@ -958,7 +953,6 @@ def main(args: argparse.Namespace):
|
||||
tokenizer=tokenizer,
|
||||
input_requests=input_requests,
|
||||
logprobs=args.logprobs,
|
||||
best_of=args.best_of,
|
||||
request_rate=args.request_rate,
|
||||
burstiness=args.burstiness,
|
||||
disable_tqdm=args.disable_tqdm,
|
||||
@@ -983,7 +977,6 @@ def main(args: argparse.Namespace):
|
||||
result_json["backend"] = backend
|
||||
result_json["model_id"] = model_id
|
||||
result_json["tokenizer_id"] = tokenizer_id
|
||||
result_json["best_of"] = args.best_of
|
||||
result_json["num_prompts"] = args.num_prompts
|
||||
|
||||
# Metadata
|
||||
@@ -1081,13 +1074,6 @@ if __name__ == "__main__":
|
||||
help=
|
||||
"Name or path of the tokenizer, if not using the default tokenizer.", # noqa: E501
|
||||
)
|
||||
parser.add_argument(
|
||||
"--best-of",
|
||||
type=int,
|
||||
default=1,
|
||||
help="Generates `best_of` sequences per prompt and "
|
||||
"returns the best one.",
|
||||
)
|
||||
parser.add_argument("--use-beam-search", action="store_true")
|
||||
parser.add_argument(
|
||||
"--num-prompts",
|
||||
|
||||
Reference in New Issue
Block a user