biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Bugfix] Fix SLA tuner initialization (#27355)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-10-23 11:43:04 +08:00
committed by GitHub
parent 2566dca2a9
commit 6738e4a093
2 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/benchmarks/sweep/serve.py
View File

@@ -66,6 +66,8 @@ def run_benchmark(
): ):
benchmark_cmd = [ benchmark_cmd = [
*bench_overrides.apply_to_cmd(bench_cmd), *bench_overrides.apply_to_cmd(bench_cmd),
"--percentile-metrics",
"ttft,tpot,itl,e2el",
"--save-result", "--save-result",
"--result-dir", "--result-dir",
str(output_path.parent), str(output_path.parent),

3
vllm/benchmarks/sweep/serve_sla.py
View File

@@ -401,7 +401,8 @@ class SweepServeSLAArgs(SweepServeArgs):
@classmethod @classmethod
def from_cli_args(cls, args: argparse.Namespace): def from_cli_args(cls, args: argparse.Namespace):
base_args = super().from_cli_args(args) # NOTE: Don't use super() as `from_cli_args` calls `cls()`
base_args = SweepServeArgs.from_cli_args(args)
if args.sla_params: if args.sla_params:
sla_params = SLASweep.read_json(args.sla_params) sla_params = SLASweep.read_json(args.sla_params)