onnxruntime
Implement new experimental lookup-based matrix multiplication method(TMAC)
#26695
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
52
Changes
View On
GitHub
Implement new experimental lookup-based matrix multiplication method(TMAC)
#26695
jambayk
merged 52 commits into
main
from
vraspar/lut-gemm
init code structure for matmul 2 bits
5484560d
add and pass q4dq tests for q2bit - rename file and test name later
8c1cfe11
some fixes
f6f22e30
add apis to neon and other avxs
3e1a9514
fix neon build
01300610
disable 2bit test
b4aad013
2 bit quantize to support model builder
ff531cbe
Merge remote-tracking branch 'msft/main' into carzh/bitnet-reverse-la…
6849ea2c
fix compile errors
e85431e5
resolve build failure update
96427403
2 bits check
892222a4
fixed bug causing int8 tests to fail
07b7f3fc
Merge remote-tracking branch 'origin/main' into carzh/bitnet-reverse-…
5fb2edd1
lintrunner
493ebd15
prepack wip -- not prepacking b data because dispatch to check for ml…
b4b143fc
fixed dispatch issue, added acc level 4 tests, and now running into a…
534b8e6d
deep sigh
70d65889
builds somehow
ad2572b4
update
b312815d
udpate
bfeac34b
Implement Pre Packing of qweight for tmac
a5de1080
Implement Pre packing for Scales and zero points
7ff8218e
Transform zero points before interleaving
6d8e8ece
Initial implementation of tmac kernel config
5d19daf0
Move pre packing scales and zp code to qlutgemm and use tmac_params
c6000562
update
5cf99e6b
bug fixes
f9a9b47d
Fix bug in scale unpacking
5687e5e6
Fix issues with TMAC GEMM kernels and remove hard coded variables
6f084186
Fix bug in LUT table generation
6191aadb
Fix casting issue
f2de7764
add session option and clean up
9ef6d75f
Refactor QNBit GEMM Implementation for AVX2
59c00550
Refactor dispatch
457cfa37
Add test cases
bdb29823
rewrite test_sqlutgemm.cpp
289e53e0
Add more robust checking before using LUT kernels
fabae089
Merge remote-tracking branch 'origin/main' into vraspar/lut-gemm
5d8a6ee3
github-actions
commented on 2025-12-16
github-advanced-security
commented on 2025-12-16
revert graph_transform_test.cc
b1fcda14
Clean up: revert unchanged files
3eb22b08
Apply linting and clean up
f61c3d8b
Add headers, update binding, and general clean up + linting
bebcb647
Fix zero point test cases
6a2e8221
jambayk
commented on 2026-01-02
jambayk
commented on 2026-01-02
Refactor ComputeBPackedLUT to remove unused parameters and simplify f…
a19b2f6e
Merge remote-tracking branch 'origin/main' into vraspar/lut-gemm
26678b21
Fix compiler warnings
e5f80cbe
Improve error handling in TMACComputeGemm_avx2 for batch size and sca…
b518ce9e
vraspar
marked this pull request as ready for review
17 days ago
vraspar
requested a review
from
edgchen1
17 days ago
edgchen1
commented on 2026-01-06
Apply feedback and use PrePacking
f94e51ef
vraspar
added
release:1.24.0
update platform.cpp
7b708ad8
use MLAS_THROW_EX for qlutgemm.cpp
58e93ec2
hariharans29
commented on 2026-01-11
hariharans29
commented on 2026-01-11
hariharans29
commented on 2026-01-11
hariharans29
commented on 2026-01-11
hariharans29
commented on 2026-01-11
hariharans29
commented on 2026-01-11
Add LUT GEMM 2-bit tests and fix Python quantization reference implem…
469cde7d
vraspar
requested a review
from
hariharans29
6 days ago
vraspar
requested a review
from
edgchen1
6 days ago
Merge remote-tracking branch 'origin/main' into vraspar/lut-gemm
48fd9829
hariharans29
commented on 2026-01-15
hariharans29
commented on 2026-01-15
hariharans29
approved these changes on 2026-01-15
hariharans29
commented on 2026-01-15
jambayk
merged
8e050d16
into main
4 days ago
jambayk
deleted the vraspar/lut-gemm branch
4 days ago
hariharans29
commented on 2026-01-16
hariharans29
commented on 2026-01-16
hariharans29
commented on 2026-01-16
Login to write a write a comment.
Login via GitHub
Reviewers
hariharans29
jambayk
edgchen1
github-actions
github-advanced-security
Assignees
No one assigned
Labels
release:1.24.0
Milestone
No milestone
Login to write a write a comment.
Login via GitHub