Skip to content

[https://nvbugs/5747938][fix] Use local tokenizer #10230

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

Open
LinPoly wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −5
Open

[https://nvbugs/5747938][fix] Use local tokenizer #10230

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
2 changes: 1 addition & 1 deletion examples/serve/aiperf_client.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@

aiperf profile \
-m TinyLlama-1.1B-Chat-v1.0 \
--tokenizer TinyLlama/TinyLlama-1.1B-Chat-v1.0 \
--tokenizer ${TOKENIZER_PATH:-TinyLlama/TinyLlama-1.1B-Chat-v1.0} \
--endpoint-type chat \
--random-seed 123 \
--synthetic-input-tokens-mean 128 \
Expand Down
6 changes: 2 additions & 4 deletions tests/unittest/llmapi/apps/_test_trtllm_serve_example.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,17 +1,14 @@
import json
import os
import subprocess
import sys
import tempfile

import pytest
import yaml

from ..test_llm import get_model_path
from .openai_server import RemoteOpenAIServer

sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
from test_llm import get_model_path


@pytest.fixture(scope="module", ids=["TinyLlama-1.1B-Chat"])
def model_name():
Expand All @@ -36,6 +33,7 @@ def temp_extra_llm_api_options_file():
@pytest.fixture(scope="module")
def server(model_name: str, temp_extra_llm_api_options_file: str):
model_path = get_model_path(model_name)
os.environ["TOKENIZER_PATH"] = model_path
# fix port to facilitate concise trtllm-serve examples
args = ["--extra_llm_api_options", temp_extra_llm_api_options_file]
with RemoteOpenAIServer(model_path, args, port=8000) as remote_server:
Expand Down
Loading