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

[CI/Build] drop support for Python 3.8 EOL (#8464)

Browse Source 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
This commit is contained in:
Aaron Pham
2024-11-06 02:11:55 -05:00
committed by GitHub
parent 4be3a45158
commit 21063c11c7
115 changed files with 239 additions and 321 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
benchmarks/backend_request_func.py
View File

@ -79,7 +79,7 @@ async def async_request_tgi(
# any data, we should skip it.
if chunk_bytes.startswith(":"):
continue
chunk = remove_prefix(chunk_bytes, "data:")
chunk = chunk_bytes.removeprefix("data:")
data = json.loads(chunk)
timestamp = time.perf_counter()
@ -144,8 +144,8 @@ async def async_request_trt_llm(
if not chunk_bytes:
continue
chunk = remove_prefix(chunk_bytes.decode("utf-8"),
"data:")
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data:")
data = json.loads(chunk)
output.generated_text += data["text_output"]
@ -261,8 +261,8 @@ async def async_request_openai_completions(
if not chunk_bytes:
continue
chunk = remove_prefix(chunk_bytes.decode("utf-8"),
"data: ")
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data: ")
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
@ -349,8 +349,8 @@ async def async_request_openai_chat_completions(
if not chunk_bytes:
continue
chunk = remove_prefix(chunk_bytes.decode("utf-8"),
"data: ")
chunk = chunk_bytes.decode("utf-8").removeprefix(
"data: ")
if chunk == "[DONE]":
latency = time.perf_counter() - st
else:
@ -389,14 +389,6 @@ 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
def get_model(pretrained_model_name_or_path: str) -> str:
if os.getenv('VLLM_USE_MODELSCOPE', 'False').lower() == 'true':
from modelscope import snapshot_download

6
benchmarks/kernels/benchmark_machete.py
View File

@ -269,10 +269,10 @@ def run_square_bench(args):
def run_range_bench(args):
m_start, k_start, n_start = [int(x) for x in args.dim_start.split(",")]
m_end, k_end, n_end = [int(x) for x in args.dim_end.split(",")]
m_start, k_start, n_start = (int(x) for x in args.dim_start.split(","))
m_end, k_end, n_end = (int(x) for x in args.dim_end.split(","))
m_increment, k_increment, n_increment = \
[int(x) for x in args.dim_increment.split(",")]
(int(x) for x in args.dim_increment.split(","))
Ms = list(range(m_start, m_end + 1, m_increment))
Ks = list(range(k_start, k_end + 1, k_increment))
Ns = list(range(n_start, n_end + 1, n_increment))