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

Replace lstrip() with removeprefix() to fix Ruff linter warning (#2958)

Browse Source
This commit is contained in:
Ronen Schaffer
2024-03-16 06:01:30 +02:00
committed by GitHub
parent 3123f15138
commit 14e3f9a1b2
2 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
benchmarks/backend_request_func.py
View File

@@ -64,7 +64,7 @@ async def async_request_tgi(
output.ttft = ttft
output.latency = time.perf_counter() - st
body = data.decode("utf-8").lstrip("data:")
body = remove_prefix(data.decode("utf-8"), "data:")
output.generated_text = json.loads(body)["generated_text"]
output.success = True
else:
@@ -158,7 +158,7 @@ async def async_request_trt_llm(
output.ttft = ttft
output.latency = time.perf_counter() - st
body = data.decode("utf-8").lstrip("data:")
body = remove_prefix(data.decode("utf-8"), "data:")
output.generated_text = json.loads(body)["text_output"]
output.success = True
@@ -255,7 +255,7 @@ async def async_request_openai_completions(
if not chunk:
continue
chunk = chunk.decode("utf-8").lstrip("data: ")
chunk = remove_prefix(chunk.decode("utf-8"), "data: ")
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
@@ -322,7 +322,7 @@ async def async_request_openai_chat_completions(
if not chunk:
continue
chunk = chunk.decode("utf-8").lstrip("data: ")
chunk = remove_prefix(chunk.decode("utf-8"), "data: ")
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
@@ -344,6 +344,13 @@ async def async_request_openai_chat_completions(
return output
# Since vllm must support Python 3.8, we can't use str.removeprefix(prefix) introduced in Python 3.9
def remove_prefix(text: str, prefix: str) -> str:
if text.startswith(prefix):
return text[len(prefix):]
return text
ASYNC_REQUEST_FUNCS = {
"tgi": async_request_tgi,
"vllm": async_request_vllm,