Skip to content

[https://nvbugs/5601203] [fix]Restrict fp8 blockscale moe case #8583

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
wants to merge 2 commits into
base: release/1.1
Choose a base branch
from
Open

[https://nvbugs/5601203] [fix]Restrict fp8 blockscale moe case #8583

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
93870b6
[https://nvbugs/5601203] [fix]Restrict fp8 blocksacle moe case
VALLIS-NERIA Oct 22, 2025
fc9bab7
Fix comment typo
VALLIS-NERIA Oct 22, 2025
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
6 changes: 4 additions & 2 deletions tests/integration/defs/examples/serve/test_serve.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import time

import requests
from defs.conftest import llm_models_root, skip_pre_hopper
from defs.conftest import llm_models_root, skip_no_hopper
from defs.trt_test_alternative import popen, print_error, print_info
from openai import OpenAI
from requests.exceptions import RequestException
Expand Down Expand Up @@ -92,9 +92,11 @@ def check_openai_chat_completion(http_port="8000",
raise


@skip_pre_hopper
@skip_no_hopper
def test_extra_llm_api_options(serve_test_root):
test_configs_root = f"{serve_test_root}/test_configs"

# moe backend = CUTLASS which only supports fp8 blockscale on Hopper
config_file = f"{test_configs_root}/Qwen3-30B-A3B-FP8.yml"
model_path = f"{llm_models_root()}/Qwen3/Qwen3-30B-A3B-FP8"

Expand Down
Loading