Skip to content

Add interleave mode for split qkv norm rope #503

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
iforgetmyname merged 2 commits into from
May 27, 2026
Merged

Add interleave mode for split qkv norm rope #503

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
960568a
Add interleave mode for split qkv norm rope
McZyWu May 19, 2026
ec73658
lint checks
McZyWu May 19, 2026
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
212 changes: 160 additions & 52 deletions python/sgl_kernel_npu/sgl_kernel_npu/norm/split_qkv_rmsnorm_rope.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ def split_qkv_rmsnorm_rope_kernel(
HALF_ROPE_DIM: tl.constexpr,
PASS_DIM: tl.constexpr,
DO_PARTIAL: tl.constexpr,
DO_HALF: tl.constexpr,
):
row_pid = tl.program_id(0)
col_pid = tl.program_id(1)
Expand Down Expand Up @@ -74,6 +75,28 @@ def split_qkv_rmsnorm_rope_kernel(
sc_offsets = row_idx * ROPE_DIM + tl.arange(0, ROPE_DIM)
sin = (tl.load(sin_ptr + sc_offsets)).reshape(1, ROPE_DIM)
cos = (tl.load(cos_ptr + sc_offsets)).reshape(1, ROPE_DIM)
if not DO_HALF:
sin_half = al.extract_slice(
sin, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 1)
)
cos_half = al.extract_slice(
cos, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 1)
)
sin = tl.zeros((1, ROPE_DIM), dtype=sin_half.dtype)
sin = al.insert_slice(
sin, sin_half, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)
sin = al.insert_slice(
sin, sin_half, offsets=(0, 1), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)

cos = tl.zeros((1, ROPE_DIM), dtype=cos_half.dtype)
cos = al.insert_slice(
cos, cos_half, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)
cos = al.insert_slice(
cos, cos_half, offsets=(0, 1), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)
if DO_PARTIAL:
rot_x = al.extract_slice(
normalized_values,
Expand All @@ -89,33 +112,63 @@ def split_qkv_rmsnorm_rope_kernel(
)
else:
rot_x = normalized_values
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, HALF_ROPE_DIM),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
if DO_HALF:
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, HALF_ROPE_DIM),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
else:
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, 1),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
cat_x = tl.zeros((Q_BLOCK_SIZE // HEAD_DIM, ROPE_DIM), dtype=tl.bfloat16)
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, HALF_ROPE_DIM),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
if DO_HALF:
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, HALF_ROPE_DIM),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
else:
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, 1),
sizes=(Q_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
Comment thread
McZyWu marked this conversation as resolved.
roped_q = cat_x * sin + rot_x * cos
if DO_PARTIAL:
normalized_values = al.insert_slice(
Expand Down Expand Up @@ -182,6 +235,29 @@ def split_qkv_rmsnorm_rope_kernel(
sin = (tl.load(sin_ptr + sc_offsets)).reshape(1, ROPE_DIM)
cos = (tl.load(cos_ptr + sc_offsets)).reshape(1, ROPE_DIM)

if not DO_HALF:
sin_half = al.extract_slice(
sin, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 1)
)
cos_half = al.extract_slice(
cos, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 1)
)
sin = tl.zeros((1, ROPE_DIM), dtype=sin_half.dtype)
sin = al.insert_slice(
sin, sin_half, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)
sin = al.insert_slice(
sin, sin_half, offsets=(0, 1), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)

cos = tl.zeros((1, ROPE_DIM), dtype=cos_half.dtype)
cos = al.insert_slice(
cos, cos_half, offsets=(0, 0), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)
cos = al.insert_slice(
cos, cos_half, offsets=(0, 1), sizes=(1, HALF_ROPE_DIM), strides=(1, 2)
)

if DO_PARTIAL:
rot_x = al.extract_slice(
normalized_values,
Expand All @@ -197,33 +273,63 @@ def split_qkv_rmsnorm_rope_kernel(
)
else:
rot_x = normalized_values
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, HALF_ROPE_DIM),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
if DO_HALF:
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, HALF_ROPE_DIM),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
else:
x1 = al.extract_slice(
rot_x,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
x2 = al.extract_slice(
rot_x,
offsets=(0, 1),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
cat_x = tl.zeros((KV_BLOCK_SIZE // HEAD_DIM, ROPE_DIM), dtype=tl.bfloat16)
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, HALF_ROPE_DIM),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
if DO_HALF:
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, HALF_ROPE_DIM),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 1),
)
else:
cat_x = al.insert_slice(
cat_x,
-x2,
offsets=(0, 0),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
cat_x = al.insert_slice(
cat_x,
x1,
offsets=(0, 1),
sizes=(KV_BLOCK_SIZE // HEAD_DIM, HALF_ROPE_DIM),
strides=(1, 2),
)
roped_k = cat_x * sin + rot_x * cos
if DO_PARTIAL:
normalized_values = al.insert_slice(
Expand Down Expand Up @@ -281,6 +387,7 @@ def split_qkv_rmsnorm_rope(
k_weight=None,
q_bias=None,
k_bias=None,
is_neox_style=True,
Comment thread
iforgetmyname marked this conversation as resolved.
):
_, num_vectorcore = get_device_properties()

Expand Down Expand Up @@ -329,6 +436,7 @@ def split_qkv_rmsnorm_rope(
rope_dim // 2,
head_dim - rope_dim,
DO_PARTIAL=(head_dim != rope_dim),
DO_HALF=is_neox_style,
)

return q_output, k_output, v_output
Expand Down
Loading