[Kernel] [Quantization] Add MXFP4 and bias support for marlin kernel (#22428)

Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
Signed-off-by: Jinzhen Lin <linjinzhen@hotmail.com>
Signed-off-by: Huzaifa Sidhpurwala <huzaifas@redhat.com>
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Animesh Jain <anijain@umich.edu>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: kf <kuanfu.liu@embeddedllm.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Signed-off-by: yan <yan.ma@intel.com>
Signed-off-by: Yan Ma <yan.ma@intel.com>
Signed-off-by: Xiao Liu <xiszishu@gmail.com>
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Andy Xie <andy.xning@gmail.com>
Signed-off-by: Haibin Lin <haibin.lin@bytedance.com>
Signed-off-by: David Ben-David <davidb@pliops.com>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Signed-off-by: Abirdcfly <fp544037857@gmail.com>
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: huangweixiao <huangweixiao@msh.team>
Signed-off-by: alyosha-swamy <raghav@arcee.ai>
Signed-off-by: Eric Hanley <ericehanley@google.com>
Signed-off-by: Abatom <abzhonghua@gmail.com>
Signed-off-by: CLFutureX <775523362@qq.com>
Signed-off-by: Linkun Chen <github@lkchen.net>
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: tlipoca9 <tlipoca9@gmail.com>
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Benji Beck <benjibeck@meta.com>
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: LucasWilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Zhang Jason <ning.zhang2@amd.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: asafg <asafg@ai21.com>
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Lain <fusiyuan2000@hotmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: QscQ <qscqesze@gmail.com>
Signed-off-by: qingjun <qingjun@minimaxi.com>
Signed-off-by: Syed Muhammad Bin Asif <syedmba7@connect.hku.hk>
Signed-off-by: Lionel Villard <villard@us.ibm.com>
Signed-off-by: ycyaw66 <497410282@qq.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: Linkun <github@lkchen.net>
Signed-off-by: Moritz Sanft <58110325+msanft@users.noreply.github.com>
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Adrian Garcia <adrian.garcia@inceptionai.ai>
Signed-off-by: shaojunqi <shaojunqi.sjq@alibaba-inc.com>
Signed-off-by: Ricardo Decal <rdecal@anyscale.com>
Signed-off-by: Andrew Chan <andrewkchan.akc@gmail.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Shu Wang <shuw@nvidia.com>
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: XIn Li <xinli@nvidia.com>
Signed-off-by: Junhao Li <junhao@ubicloud.com>
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Signed-off-by: <zyy1102000@gmail.com>
Signed-off-by: Guy Stone <guys@spotify.com>
Signed-off-by: <yyweiss@gmail.com>
Signed-off-by: yyw <yyweiss@gmail.com>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Signed-off-by: Pradyun Ramadorai <pradyunr@amazon.com>
Signed-off-by: Pradyun92 <142861237+Pradyun92@users.noreply.github.com>
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: rongfu.leng <rongfu.leng@daocloud.io>
Co-authored-by: Huzaifa Sidhpurwala <huzaifas@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Animesh Jain <jainanimesh2305@yahoo.com>
Co-authored-by: Rui Qiao <161574667+ruisearch42@users.noreply.github.com>
Co-authored-by: XiongfeiWei <isaacwxf23@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: JartX <sagformas@gmail.com>
Co-authored-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: kf <kuanfu.liu@embeddedllm.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Dipika Sikka <dipikasikka1@gmail.com>
Co-authored-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
Co-authored-by: Yong Hoon Shin <48474650+sarckk@users.noreply.github.com>
Co-authored-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
Co-authored-by: Yuxuan Zhang <2448370773@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Yan Ma <yan.ma@intel.com>
Co-authored-by: Xiao <xiszishu@gmail.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Ning Xie <andy.xning@gmail.com>
Co-authored-by: H <linhaibin.eric@gmail.com>
Co-authored-by: David Ben-David <sdavidbd@gmail.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
Co-authored-by: TankNee <nee@tanknee.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Seiji Eicher <58963096+eicherseiji@users.noreply.github.com>
Co-authored-by: ZiTian.Zhao <zitian.zhao@tencentmusic.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Abirdcfly <fp544037857@gmail.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Chenxi Yang <cxyang@cs.utexas.edu>
Co-authored-by: Chenxi Yang <cxyang@meta.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Weixiao Huang <hwx.simle@gmail.com>
Co-authored-by: Raghav Ravishankar <113712354+alyosha-swamy@users.noreply.github.com>
Co-authored-by: ericehanley <ericehanley@google.com>
Co-authored-by: Zhonghua Deng <abzhonghua@gmail.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: PiteXChen <44110731+CLFutureX@users.noreply.github.com>
Co-authored-by: lkchen <github@lkchen.net>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: tlipoca9 <160737620+tlipoca9@users.noreply.github.com>
Co-authored-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: wang.yuqi <noooop@126.com>
Co-authored-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Siyuan Liu <lsiyuan@google.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Zhang Jason <ning.zhang2@amd.com>
Co-authored-by: Asaf Joseph Gardin <39553475+Josephasafg@users.noreply.github.com>
Co-authored-by: asafg <asafg@ai21.com>
Co-authored-by: Lain <siyuanf@nvidia.com>
Co-authored-by: tc-mb <157115220+tc-mb@users.noreply.github.com>
Co-authored-by: imning3 <hbning@pku.edu.cn>
Co-authored-by: Maximilien de Bayser <mbayser@br.ibm.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: Tao He <linzhu.ht@alibaba-inc.com>
Co-authored-by: qscqesze <qingjun@minimaxi.com>
Co-authored-by: Syed Muhammad Bin Asif <92625830+syedmba@users.noreply.github.com>
Co-authored-by: Lionel Villard <villard@us.ibm.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: ycyaw66 <497410282@qq.com>
Co-authored-by: Moritz Sanft <58110325+msanft@users.noreply.github.com>
Co-authored-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: Adrián García García <adrigarvk8@gmail.com>
Co-authored-by: Michael Goin <mgoin@redhat.com>
Co-authored-by: JaceyShao <65159281+JaceyShao@users.noreply.github.com>
Co-authored-by: shaojunqi <shaojunqi.sjq@alibaba-inc.com>
Co-authored-by: Ricardo Decal <crypdick@users.noreply.github.com>
Co-authored-by: Andrew Chan <andrewkchan.akc@gmail.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Zhiyu <zhiyuc@nvidia.com>
Co-authored-by: Shu Wang <shuw@nvidia.com>
Co-authored-by: XIn Li <xinli@nvidia.com>
Co-authored-by: Junhao Li <streaver91@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: Hong Hanh <hanh.usth@gmail.com>
Co-authored-by: Daniel Serebrenik <74646983+pliops-daniels@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Guy Stone <guys@spotify.com>
Co-authored-by: yyweiss <70619747+yyweiss@users.noreply.github.com>
Co-authored-by: Pradyun92 <142861237+Pradyun92@users.noreply.github.com>
Co-authored-by: Pradyun Ramadorai <pradyunr@amazon.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
This commit is contained in:
Jinzhen Lin
2025-08-14 11:23:22 -07:00
committed by GitHub
co-authored by rongfu.leng Huzaifa Sidhpurwala gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Russell Bryant Varun Sundar Rabindranath Varun Sundar Rabindranath Harry Mellor Jee Jee Li Michael Goin Animesh Jain Rui Qiao XiongfeiWei Nick Hill Wentao Ye JartX fhl2000 vllmellm kf Nicolò Lucchesi Dipika Sikka Sage Moore tjtanaavllm Yong Hoon Shin Chih-Chieh Yang Roger Wang Vadim Gimpelson Yuxuan Zhang Isotr0py Cyrus Leung Thomas Parnell Yan Ma Xiao jiahanc Isotr0py Ye Qi Roberto L. Castro Ning Xie H David Ben-David David Ben-David Woosuk Kwon Li, Jiang <jiang1.li@intel.com> TankNee Cyrus Leung Seiji Eicher ZiTian.Zhao 22quinn Abirdcfly Giancarlo Delfin Chenxi Yang Chenxi Yang Tyler Michael Smith Weixiao Huang Raghav Ravishankar ericehanley Zhonghua Deng Po-Han Huang PiteXChen lkchen TJian Gregory Shtrasberg tlipoca9 elvischenv wang.yuqi Benji Beck youkaichao Siyuan Liu Benjamin Chislett LiuXiaoxuanPKU simon-mo Chen Zhang Hongxia Yang Minseok Lee Yongye Zhu Lucas Wilkinson Zhang Jason Asaf Joseph Gardin asafg Lain tc-mb imning3 Maximilien de Bayser Kunshang Ji Tao He qscqesze Syed Muhammad Bin Asif Lionel Villard WeiQing Chen ycyaw66 Moritz Sanft Ming Yang Adrián García García Michael Goin JaceyShao shaojunqi Ricardo Decal Andrew Chan fxmarty-amd Andrew Sansom Zhiyu Shu Wang XIn Li Junhao Li Chauncey iAmir97 iAmir97 Hong Hanh Daniel Serebrenik yewentao256 Guy Stone yyweiss Pradyun92 Pradyun Ramadorai Nicolò Lucchesi
parent ab9f2cfd19
commit 33c63e9547
34 changed files with 1128 additions and 324 deletions
+74 -21
View File
@@ -19,10 +19,11 @@ from vllm.model_executor.layers.quantization.qqq import (
from vllm.model_executor.layers.quantization.utils.marlin_utils import (
GPTQ_MARLIN_MAX_PARALLEL, GPTQ_MARLIN_MIN_THREAD_N,
MARLIN_SUPPORTED_GROUP_SIZES, marlin_make_empty_g_idx,
marlin_make_workspace_new, marlin_permute_scales,
marlin_make_workspace_new, marlin_permute_bias, marlin_permute_scales,
query_marlin_supported_quant_types)
from vllm.model_executor.layers.quantization.utils.marlin_utils_fp4 import (
FP4_MARLIN_SUPPORTED_GROUP_SIZES, rand_marlin_weight_fp4_like)
FP4_MARLIN_SUPPORTED_GROUP_SIZES, rand_marlin_weight_mxfp4_like,
rand_marlin_weight_nvfp4_like)
from vllm.model_executor.layers.quantization.utils.marlin_utils_fp8 import (
marlin_quant_fp8_torch)
from vllm.model_executor.layers.quantization.utils.marlin_utils_test import (
@@ -39,7 +40,7 @@ from vllm.scalar_type import scalar_types
ACT_ORDER_OPTS = [False, True]
K_FULL_OPTS = [False, True]
USE_ATOMIC_ADD_OPTS = [False, True]
USE_FP32_REDUCE_OPTS = [False, True]
USE_FP32_REDUCE_OPTS = [True]
MARLIN_K_CHUNKS = [128]
MARLIN_N_CHUNKS = [64, 256]
@@ -202,17 +203,10 @@ def test_awq_marlin_repack(k_chunk, n_chunk, quant_type, group_size,
@pytest.mark.parametrize("is_k_full", K_FULL_OPTS)
@pytest.mark.parametrize("use_atomic_add", USE_ATOMIC_ADD_OPTS)
@pytest.mark.parametrize("use_fp32_reduce", USE_FP32_REDUCE_OPTS)
def test_gptq_marlin_gemm(
k_chunk,
n_chunk,
quant_type,
group_size,
mnk_factors,
act_order,
is_k_full,
use_atomic_add,
use_fp32_reduce,
):
@pytest.mark.parametrize("dtype", DTYPES)
def test_gptq_marlin_gemm(k_chunk, n_chunk, quant_type, group_size,
mnk_factors, act_order, is_k_full, use_atomic_add,
use_fp32_reduce, dtype):
m_factor, n_factor, k_factor = mnk_factors
has_zp = quant_type in [scalar_types.uint4, scalar_types.uint8]
@@ -231,14 +225,23 @@ def test_gptq_marlin_gemm(
if size_k % group_size != 0:
return
a_input = rand_data((size_m, size_k))
b_weight = rand_data((size_k, size_n))
a_input = rand_data((size_m, size_k), dtype)
b_weight = rand_data((size_k, size_n), dtype)
if quant_type == scalar_types.float4_e2m1f:
if group_size != 16 or act_order:
if group_size not in [16, 32] or act_order:
return
w_ref, marlin_q_w, marlin_s, marlin_s2 = rand_marlin_weight_fp4_like(
b_weight.T, group_size)
if group_size == 32 and dtype == torch.float16:
return
if group_size == 16:
w_ref, marlin_q_w, marlin_s, marlin_s2 = \
rand_marlin_weight_nvfp4_like(b_weight.T, group_size)
else:
w_ref, marlin_q_w, marlin_s = \
rand_marlin_weight_mxfp4_like(b_weight.T, group_size)
marlin_s2 = None
g_idx = None
sort_indices = None
marlin_zp = None
@@ -272,8 +275,8 @@ def test_gptq_marlin_gemm(
workspace = marlin_make_workspace_new(w_ref.device)
opcheck(torch.ops._C.gptq_marlin_gemm,
(a_input, None, marlin_q_w, marlin_s, marlin_s2, marlin_zp, g_idx,
sort_indices, workspace, quant_type.id, a_input.shape[0],
(a_input, None, marlin_q_w, None, marlin_s, marlin_s2, marlin_zp,
g_idx, sort_indices, workspace, quant_type.id, a_input.shape[0],
b_weight.shape[1], a_input.shape[1], is_k_full, use_atomic_add,
use_fp32_reduce, False),
test_utils=DEFAULT_OPCHECK_TEST_UTILS)
@@ -282,6 +285,7 @@ def test_gptq_marlin_gemm(
a_input,
None,
marlin_q_w,
None,
marlin_s,
marlin_s2,
marlin_zp,
@@ -418,6 +422,7 @@ def test_hqq_marlin_gemm(
a_input,
None,
marlin_w_q,
None,
marlin_s,
None,
marlin_zp,
@@ -531,6 +536,7 @@ def test_marlin_gemm_subset_input():
a_input,
None,
marlin_q_w,
None,
marlin_s,
None,
marlin_zp,
@@ -555,6 +561,53 @@ def test_marlin_gemm_subset_input():
assert max_diff < 0.04
@pytest.mark.parametrize("size_m", [1, 256])
def test_marlin_gemm_with_bias(size_m):
quant_type = scalar_types.uint4b8
group_size = 128
size_k, size_n = 1024, 2048
a_input = rand_data((size_m, size_k))
b_weight = rand_data((size_k, size_n))
b_bias = rand_data((size_n, )) * 10
marlin_bias = marlin_permute_bias(b_bias)
w_ref, marlin_q_w, marlin_s, g_idx, sort_indices, _ = marlin_quantize(
b_weight, quant_type, group_size, False)
marlin_zp = marlin_make_empty_g_idx(marlin_s.device)
workspace = marlin_make_workspace_new(a_input.device)
output = ops.gptq_marlin_gemm(
a_input,
None,
marlin_q_w,
marlin_bias,
marlin_s,
None,
marlin_zp,
g_idx,
sort_indices,
workspace,
quant_type,
a_input.shape[0],
b_weight.shape[1],
a_input.shape[1],
is_k_full=True,
use_atomic_add=False,
use_fp32_reduce=True,
is_zp_float=False,
)
output_ref = torch.matmul(a_input, w_ref) + b_bias.view(1, -1)
torch.cuda.synchronize()
max_diff = compute_max_diff(output, output_ref)
assert max_diff < 0.04
def test_marlin_gemm_opcheck():
size_m = 2048
size_n = 4096