xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-24 16:31:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Benchmark] Fix Value of type "SampleRequest" is not indexable (#18032)

Browse Source 
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
This commit is contained in:
Brayden Zhong 2025-06-20 00:28:55 -04:00 committed by GitHub
parent b6bad3d186
commit 5aa4a015ce
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
benchmarks/benchmark_throughput.py
View File

@ -97,7 +97,7 @@ def run_vllm(
assert lora_requests is None, "BeamSearch API does not support LoRA" assert lora_requests is None, "BeamSearch API does not support LoRA"
prompts = [request.prompt for request in requests] prompts = [request.prompt for request in requests]
# output_len should be the same for all requests. # output_len should be the same for all requests.
output_len = requests[0][2] output_len = requests[0].expected_output_len
for request in requests: for request in requests:
assert request.expected_output_len == output_len assert request.expected_output_len == output_len
start = time.perf_counter() start = time.perf_counter()

2
vllm/benchmarks/throughput.py
View File

@ -84,7 +84,7 @@ def run_vllm(
assert lora_requests is None, "BeamSearch API does not support LoRA" assert lora_requests is None, "BeamSearch API does not support LoRA"
prompts = [request.prompt for request in requests] prompts = [request.prompt for request in requests]
# output_len should be the same for all requests. # output_len should be the same for all requests.
output_len = requests[0][2] output_len = requests[0].expected_output_len
for request in requests: for request in requests:
assert request.expected_output_len == output_len assert request.expected_output_len == output_len
start = time.perf_counter() start = time.perf_counter()