Skip to content

[Inference] Fix quant bits order #5681

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
merged 1 commit into from
Apr 30, 2024
Merged

[Inference] Fix quant bits order #5681

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
8 changes: 4 additions & 4 deletions extensions/csrc/funcs/cast_functor.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -390,7 +390,7 @@ COLOSSAL_CAST_FUNCTOR_SPECIALIZATION(
static_cast<uint16_t>(CastFunctor<float, uint8_t>()(val.x));
uint16_t tmp2 =
static_cast<uint16_t>(CastFunctor<float, uint8_t>()(val.y));
uint16_t res = (tmp1 << 8U) | tmp2;
uint16_t res = (tmp2 << 8U) | tmp1;
return res;
}))

Expand All @@ -401,8 +401,8 @@ COLOSSAL_CAST_FUNCTOR_SPECIALIZATION(float4, uint32_t, DEVICE, STMTS_WRAPPER({
b = CastFunctor<float, uint8_t>()(val.y);
c = CastFunctor<float, uint8_t>()(val.z);
d = CastFunctor<float, uint8_t>()(val.w);
return (a << 24U) | (b << 16U) |
(c << 8U) | d;
return (d << 24U) | (c << 16U) |
(b << 8U) | a;
}))

// fp8x4 -> float4_
Expand Down Expand Up @@ -458,7 +458,7 @@ COLOSSAL_CAST_FUNCTOR_SPECIALIZATION(
static_cast<uint16_t>(CastFunctor<__nv_bfloat16, uint8_t>()(val.x));
uint16_t b =
static_cast<uint16_t>(CastFunctor<__nv_bfloat16, uint8_t>()(val.y));
return (a << 8U) | b;
return (b << 8U) | a;
}))

// bf164 -> fp8x4
Expand Down