Skip to content

[TRTLLM-9457] Add cute dsl fp8 gemm for Blackwell #10130

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

Draft
yifeizhang-c wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[TRTLLM-9457] Add cute dsl fp8 gemm for Blackwell #10130

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
10 changes: 10 additions & 0 deletions examples/llm-api/quickstart_advanced.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,14 @@ def add_llm_args(parser):
default=None,
nargs='+')

# cute dsl op configs
parser.add_argument('--use_cute_dsl_blockscaling_mm',
default=False,
action='store_true')
parser.add_argument('--use_cute_dsl_blockscaling_bmm',
default=False,
action='store_true')

return parser


Expand Down Expand Up @@ -267,6 +275,8 @@ def setup_llm(args, **kwargs):
trust_remote_code=args.trust_remote_code,
gather_generation_logits=args.return_generation_logits,
max_beam_width=args.max_beam_width,
use_cute_dsl_blockscaling_mm=args.use_cute_dsl_blockscaling_mm,
use_cute_dsl_blockscaling_bmm=args.use_cute_dsl_blockscaling_bmm,
**kwargs)

use_beam_search = args.max_beam_width > 1
Expand Down
Loading
Loading