Skip to content

GitLab

Unverified Commit 268d017e authored by Hongkuan Zhou's avatar Hongkuan Zhou Committed by GitHub
Browse files

fix: missing tokenizer args in sla_planner.py (#2667)

parent f19b44a9
Show whitespace changes
Inline Side-by-side
Showing with 6 additions and 1 deletion
benchmarks/profiler/profile_sla.py
View file @ 268d017e
...@@ -158,7 +158,11 @@ async def run_profile(args): ...@@ -158,7 +158,11 @@ async def run_profile(args):
base_url = client.get_service_url() base_url = client.get_service_url()
genai_perf_artifact_dir = f"{work_dir}/gap_isl{args.isl}" genai_perf_artifact_dir = f"{work_dir}/gap_isl{args.isl}"
gap_result = benchmark_prefill( gap_result = benchmark_prefill(
args.isl, genai_perf_artifact_dir, model_name, base_url=base_url args.isl,
genai_perf_artifact_dir,
model_name,
model_name,
base_url=base_url,
) )
if gap_result is not None: if gap_result is not None:
ttft = gap_result["time_to_first_token"]["avg"] ttft = gap_result["time_to_first_token"]["avg"]
...@@ -283,6 +287,7 @@ async def run_profile(args): ...@@ -283,6 +287,7 @@ async def run_profile(args):
num_request, num_request,
genai_perf_artifact_dir, genai_perf_artifact_dir,
model_name, model_name,
model_name,
base_url=base_url, base_url=base_url,
) )
if gap_result is not None: if gap_result is not None:
......
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