xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:04:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Benchmark] Enable benchmark to run with encoding_format="bytes" (#27467)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-10-24 19:16:50 +08:00 committed by GitHub
parent 3567816932
commit b7030d962b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
vllm/benchmarks/lib/endpoint_request_func.py
View File

@ -498,10 +498,17 @@ async def _run_pooling_request(
async with session.post(url=api_url, headers=headers, json=payload) as response: async with session.post(url=api_url, headers=headers, json=payload) as response:
if response.status == 200: if response.status == 200:
output.ttft = output.latency = time.perf_counter() - st output.ttft = output.latency = time.perf_counter() - st
data = await response.json()
if payload.get("encoding_format", "float") == "bytes":
metadata = json.loads(response.headers["metadata"])
usage = metadata.get("usage", {})
else:
data = await response.json()
usage = data.get("usage", {})
output.success = True output.success = True
output.generated_text = "" output.generated_text = ""
output.prompt_len = data.get("usage", {}).get("prompt_tokens", 0) output.prompt_len = usage.get("prompt_tokens", 0)
else: else:
output.success = False output.success = False
output.error = response.reason or "" output.error = response.reason or ""