Skip to content
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

update version #99

Merged
merged 2 commits into from
Oct 29, 2024
Merged

update version #99

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7bb2d01
Set __version__ (#97)
YangWang92 Oct 28, 2024
fde03de
fix compiling error (#98)
YangWang92 Oct 28, 2024
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: 5 additions & 1 deletion csrc/utils.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,7 +256,11 @@ T __device__ __forceinline__ ADD2(T a, T b) {
template <typename T>
T __device__ __forceinline__ ZERO_VALUE(T a) {
if constexpr (std::is_same<T, __bfloat16>::value) {
return __ushort_as_bfloat16((unsigned short)0x0000U);
#if defined(USE_ROCM)
return __float2bfloat16(0.0f);
#else
return __float2bfloat16_rn(0.0f);
#endif
} else if constexpr (std::is_same<T, float>::value) {
return 0.0f;
} else {
Expand Down
4 changes: 4 additions & 0 deletions setup.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,9 @@ def build_cuda_extensions():
arch_flags += ["-gencode", f"arch=compute_{cap},code=sm_{cap}"]
print(" build for compute capabilities: ==============", compute_capabilities)

# set nvcc threads
nvcc_threads = os.getenv("NVCC_THREADS") or "4"

extra_compile_args = {
"nvcc": [
"-O3",
Expand All @@ -58,6 +61,7 @@ def build_cuda_extensions():
"-U__CUDA_NO_BFLOAT16_CONVERSIONS__",
"-U__CUDA_NO_BFLOAT162_OPERATORS__",
"-U__CUDA_NO_BFLOAT162_CONVERSIONS__",
f"--threads={nvcc_threads}",
] + arch_flags,
"cxx": ["-O3", "-fopenmp", "-lgomp", "-std=c++17", "-DENABLE_BF16"],
}
Expand Down
2 changes: 1 addition & 1 deletion vptq/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,5 +3,5 @@
# Licensed under the MIT License.
# --------------------------------------------------------------------------

__version__ = "0.0.2.post1"
__version__ = "0.0.3"
from vptq.layers import AutoModelForCausalLM as AutoModelForCausalLM
Loading