Skip to content

Fix issue where input data wasn't provided to PA #542

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 22, 2024
Merged

Fix issue where input data wasn't provided to PA #542

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions src/c++/perf_analyzer/genai-perf/genai_perf/test_end_to_end.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,10 +20,10 @@
]

base_commands = {
"nim_chat": "genai-pa -s 999 -p 20000 -m llama-2-7b-chat -u http://localhost:9999--output-format openai_chat_completions --service-kind openai --endpoint v1/chat/completions",
"nim_completions": "genai-pa -s 999 -p 20000 -m llama-2-7b -u http://localhost:9999 --output-format openai_completions --service-kind openai --endpoint v1/completions",
"vllm_openai": "genai-pa -s 999 -p 20000 -m mistralai/Mistral-7B-v0.1 --output-format openai_chat_completions --service-kind openai --endpoint v1/chat/completions",
"triton_trtllm": "genai-pa -s 999 -p 20000 -m llama-2-7b -u 0.0.0.0:9999 --service-kind triton --output-format trtllm",
"nim_chat": "genai-perf -s 999 -p 20000 -m llama-2-7b-chat -u http://localhost:9999 --output-format openai_chat_completions --service-kind openai --endpoint v1/chat/completions",
"nim_completions": "genai-perf -s 999 -p 20000 -m llama-2-7b -u http://localhost:9999 --output-format openai_completions --service-kind openai --endpoint v1/completions",
"vllm_openai": "genai-perf -s 999 -p 20000 -m mistralai/Mistral-7B-v0.1 --output-format openai_chat_completions --service-kind openai --endpoint v1/chat/completions",
"triton_trtllm": "genai-perf -s 999 -p 20000 -m llama-2-7b -u 0.0.0.0:9999 --service-kind triton --output-format trtllm",
}
testname = ""

Expand Down
6 changes: 3 additions & 3 deletions src/c++/perf_analyzer/genai-perf/genai_perf/wrapper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@
import subprocess

import genai_perf.utils as utils
from genai_perf.constants import DEFAULT_GRPC_URL, LOGGER_NAME
from genai_perf.constants import DEFAULT_GRPC_URL, DEFAULT_INPUT_DATA_JSON, LOGGER_NAME
from genai_perf.llm_inputs.llm_inputs import OutputFormat

logger = logging.getLogger(LOGGER_NAME)
Expand All @@ -52,7 +52,7 @@ def add_protocol_args(args):
def build_cmd(args, extra_args):
skip_args = [
"func",
"dataset",
"input_dataset",
"input_type",
"input_format",
"model",
Expand All @@ -72,7 +72,7 @@ def build_cmd(args, extra_args):

utils.remove_file(args.profile_export_file)

cmd = f"perf_analyzer -m {args.model} --async "
cmd = f"perf_analyzer -m {args.model} --async --input-data {DEFAULT_INPUT_DATA_JSON} "
for arg, value in vars(args).items():
if arg in skip_args:
pass
Expand Down
Loading