Skip to content

Fix the get_target_compute_version for sm >= 100 #17716

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
yongwww merged 1 commit into from
Mar 7, 2025
Merged

Fix the get_target_compute_version for sm >= 100 #17716

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
12 changes: 7 additions & 5 deletions python/tvm/contrib/nvcc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,13 +292,15 @@ def get_target_compute_version(target=None):
target = target or Target.current()
if target and target.arch:
arch = target.arch.split("_")[1]
if len(arch) == 2:
major, minor = arch
return major + "." + minor
elif len(arch) == 3:
if len(arch) < 2:
raise ValueError(f"The arch is not expected {target.arch}")
if arch[-1].isalpha():
# This is for arch like "sm_90a"
major, minor, suffix = arch
suffix = arch[-1]
major = arch[:-2]
minor = arch[-2]
return major + "." + minor + "." + suffix
return arch[:-1] + "." + arch[-1]

# 3. GPU compute version
if tvm.cuda(0).exist:
Expand Down
7 changes: 5 additions & 2 deletions python/tvm/relax/vm_build.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,8 +197,11 @@ def build(
params: Optional[Dict[str, list]]
Parameters for the input IRModule that will be bound.

pipeline : str = "default_build"
The compilation pipeline to use.
relax_pipeline : str = "default"
The Relax compilation pipeline to use.

tir_pipelinie : str = "default"
The TIR compilation pipeline to use.

exec_mode: {"bytecode", "compiled"}
The execution mode.
Expand Down
Loading