Skip to content

GitLab

Unverified Commit 5aa4a015 authored by Brayden Zhong's avatar Brayden Zhong Committed by GitHub
Browse files

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


Signed-off-by: default avatarBrayden Zhong <b8zhong@uwaterloo.ca>
parent b6bad3d1
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
benchmarks/benchmark_throughput.py
View file @ 5aa4a015
...@@ -97,7 +97,7 @@ def run_vllm( ...@@ -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()
......
vllm/benchmarks/throughput.py
View file @ 5aa4a015
...@@ -84,7 +84,7 @@ def run_vllm( ...@@ -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()
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment