Skip to content

Hoist W4A8 activation quantization out of GEMM K-loop #19209

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

Open
Gasoonjia wants to merge 7 commits into
base: gh/digantdesai/53/base
Choose a base branch
from
Open

Hoist W4A8 activation quantization out of GEMM K-loop #19209

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
e1c1003
Add structured stats reporting and GPU memory tracking to Qwen3.5 MoE…
digantdesai Apr 28, 2026
ca2f5df
Update on "Add structured stats reporting and GPU memory tracking to …
digantdesai Apr 28, 2026
4f7c548
Update on "Add structured stats reporting and GPU memory tracking to …
digantdesai Apr 28, 2026
2ba0675
Update on "Add structured stats reporting and GPU memory tracking to …
digantdesai Apr 28, 2026
ab06a24
Update on "Add structured stats reporting and GPU memory tracking to …
digantdesai Apr 29, 2026
87c9947
Update on "Add structured stats reporting and GPU memory tracking to …
digantdesai Apr 29, 2026
d936717
Hoist W4A8 activation quantization out of GEMM K-loop
Gasoonjia Apr 29, 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
1 change: 0 additions & 1 deletion backends/cuda/tests/test_int4_matmul.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@
import unittest

import torch
import torch.nn as nn

from executorch.backends.cuda.triton.kernels.int4_matmul import (
dequant_w4_to_bf16,
Expand Down
3 changes: 3 additions & 0 deletions backends/cuda/triton/kernels/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
fused_moe,
fused_moe_batched,
fused_moe_batched_gemm,
fused_moe_batched_gemm_int8,
moe_align_block_size,
)

Expand All @@ -23,6 +24,8 @@
"fused_moe",
"fused_moe_batched",
"fused_moe_batched_gemm",
"fused_moe_batched_gemm_int8",
"int4_matvec",
"moe_align_block_size",
"sdpa",
"sdpa_decode_splitk",
Expand Down
Loading
Loading