mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2026-04-07 23:07:12 +08:00
Signed-off-by: Nick Hill <nhill@redhat.com> Signed-off-by: Lucas Kabela <lucaskabela@meta.com> Signed-off-by: Max de Bayser <mbayser@br.ibm.com> Signed-off-by: Andrew Sansom <andrew@protopia.ai> Signed-off-by: Boyuan Feng <boyuan@meta.com> Signed-off-by: Boyuan Feng <fby.1994@gmail.com> Signed-off-by: boyuanfeng <boyuan@meta.com> Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: JartX <sagformas@epdcenter.es> Signed-off-by: Chendi Xue <Chendi.Xue@intel.com> Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Signed-off-by: Chen Zhang <zhangch99@outlook.com> Signed-off-by: Roger Wang <hey@rogerw.io> Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: wwl2755 <wangwenlong2755@gmail.com> Signed-off-by: Manoel Marques <manoel.marques@ibm.com> Signed-off-by: Manoel Marques <manoelmrqs@gmail.com> Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn> Signed-off-by: pengdrumli <pengdrumli@tencent.com> Signed-off-by: windsonsea <haifeng.yao@daocloud.io> Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai> Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Signed-off-by: Huamin Li <3ericli@gmail.com> Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com> Signed-off-by: Rahul Tuli <rtuli@redhat.com> Signed-off-by: Yang <lymailforjob@gmail.com> Signed-off-by: Debolina Roy <debroy@redhat.com> Signed-off-by: David Chen <530634352@qq.com> Signed-off-by: wangzi <3220100013@zju.edu.cn> Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com> Signed-off-by: NickLucche <nlucches@redhat.com> Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com> Signed-off-by: Sara Kokkila Schumacher <saraks@ibm.com> Signed-off-by: Csrayz <jover@cmbchina.com> Signed-off-by: ivyilike <pww123@cmbchina.com> Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com> Signed-off-by: Bowen Wang <abmfy@icloud.com> Signed-off-by: qqma <qqma@amazon.com> Signed-off-by: ElizaWszola <ewszola@redhat.com> Signed-off-by: Lu Fang <fanglu@fb.com> Signed-off-by: Zhuohan Li <zhuohan123@gmail.com> Signed-off-by: Luka Govedič <lgovedic@redhat.com> Signed-off-by: luka <lgovedic@redhat.com> Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com> Signed-off-by: Or Ozeri <oro@il.ibm.com> Signed-off-by: Johnny Yang <johnnyyang@google.com> Signed-off-by: Alec Solder <alecs@fb.com> Signed-off-by: Alec S <10566873+alecsolder@users.noreply.github.com> Signed-off-by: Russell Bryant <rbryant@redhat.com> Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Signed-off-by: Alexander Matveev <amatveev@redhat.com> Signed-off-by: yewentao256 <zhyanwentao@126.com> Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com> Signed-off-by: Kunshang Ji <kunshang.ji@intel.com> Signed-off-by: Lucia Fang <116399278+luccafong@users.noreply.github.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com> Signed-off-by: Ming Yang <minos.future@gmail.com> Signed-off-by: Zhikaiiii <1658973216@qq.com> Signed-off-by: Andreas Hartel <andreas.hartel@aleph-alpha.com> Signed-off-by: Jee Jee Li <pandaleefree@gmail.com> Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com> Signed-off-by: wuxibin <wuxibin@bytedance.com> Signed-off-by: youkaichao <youkaichao@gmail.com> Signed-off-by: Peter Pan <Peter.Pan@daocloud.io> Signed-off-by: Peter Pan <peter.pan@daocloud.io> Signed-off-by: Nicolò Lucchesi<nicolo.lucchesi@gmail.com> Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com> Signed-off-by: Sage Moore <sage@neuralmagic.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com> Signed-off-by: Bill Nell <bnell@redhat.com> Signed-off-by: Shreeasish Kumar <shreeasish@rivosinc.com> Signed-off-by: Weida Hong <wdhongtw@google.com> Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com> Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com> Signed-off-by: Hashem Hashemi <159079214+amd-hhashemi@users.noreply.github.com> Signed-off-by: Amir Samani <asamani@nvidia.com> Signed-off-by: ElizaWszola <elizaw.9289@gmail.com> Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com> Signed-off-by: ilmarkov <markovilya197@gmail.com> Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com> Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: rouchenzi <ruochenwen@gmail.com> Signed-off-by: rouchenzi <40842833+rouchenzi@users.noreply.github.com> Signed-off-by: Andrew Xia <axia@meta.com> Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com> Signed-off-by: Corey Lowman <clowman1993@gmail.com> Signed-off-by: jpvillam <jpvillam@amd.com> Signed-off-by: dougbtv <dosmith@redhat.com> Signed-off-by: Chenxi Yang <cxyang@fb.com> Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Signed-off-by: ahao-anyscale <ahao@anyscale.com> Signed-off-by: Yan Lu <luyan@nvidia.com> Signed-off-by: baxingpiaochong <771405853@qq.com> Signed-off-by: Kyle Sayers <kylesayrs@gmail.com> Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com> Signed-off-by: Yong Hoon Shin <yhshin@meta.com> Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai> Signed-off-by: Benjamin Chislett <bchislett@nvidia.com> Signed-off-by: Ben Browning <bbrownin@redhat.com> Signed-off-by: Chengji Yao <chengjiyao@google.com> Signed-off-by: jiang1.li <jiang1.li@intel.com> Signed-off-by: Jackmin801 <ongjackm@gmail.com> Signed-off-by: Jonas M. Kübler <44084297+jmkuebler@users.noreply.github.com> Signed-off-by: taohui <taohui3@gmail.com> Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io> Signed-off-by: Shu Wang <shuw@nvidia.com> Signed-off-by: Shu Wang. <shuw@nvidia.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Signed-off-by: Duncan Moss <djm.moss@gmail.com> Signed-off-by: Shiyan Deng <dsy842974287@meta.com> Signed-off-by: Wei Wei <wwei6@meta.com> Signed-off-by: Saman Keon <samanamp@outlook.com> Signed-off-by: yangxurui <yangxurui@meituan.com> Signed-off-by: nicole-lihui <nicole.li@daocloud.io> Signed-off-by: courage17340 <courage17340@163.com> Signed-off-by: Jacob Kahn <jacobkahn1@gmail.com> Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com> Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai> Signed-off-by: zxw <1020938856@qq.com> Signed-off-by: wang.yuqi <noooop@126.com> Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Signed-off-by: chenlang <chen.lang5@zte.com.cn> Signed-off-by: Jonas Kuebler <kuebj@amazon.com> Signed-off-by: AlonKejzman <alonkeizman@gmail.com> Signed-off-by: Tao Hui <taohui3@gmail.com> Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com> Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com> Signed-off-by: Aleksandr Malyshev <maleksan@amd.com> Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com> Signed-off-by: Eugene Khvedchenya <ekhvedchenya@gmail.com> Signed-off-by: yiting.jiang <yiting.jiang@daocloud.io> Signed-off-by: xaguilar <Xavier.AguilarFruto@amd.com> Signed-off-by: Iceber Gu <caiwei95@hotmail.com> Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com> Signed-off-by: Icey <1790571317@qq.com> Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com> Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com> Co-authored-by: Nick Hill <nhill@redhat.com> Co-authored-by: Lucas Kabela <lucasakabela@gmail.com> Co-authored-by: Maximilien de Bayser <mbayser@br.ibm.com> Co-authored-by: Andrew Sansom <andrew@protopia.ai> Co-authored-by: Boyuan Feng <boyuan@meta.com> Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: JartX <sagformas@epdcenter.es> Co-authored-by: Chendi.Xue <chendi.xue@intel.com> Co-authored-by: Chauncey <chaunceyjiang@gmail.com> Co-authored-by: xin.li <xin.li@daocloud.io> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk> Co-authored-by: Chen Zhang <zhangch99@outlook.com> Co-authored-by: Roger Wang <hey@rogerw.io> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Wenlong Wang <wangwenlong2755@gmail.com> Co-authored-by: Manoel Marques <manoelmrqs@gmail.com> Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn> Co-authored-by: lirong <56789630+lirong-lirong@users.noreply.github.com> Co-authored-by: Michael Yao <haifeng.yao@daocloud.io> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: Huamin Li <3ericli@gmail.com> Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com> Co-authored-by: Simon Danielsson <70206058+simondanielsson@users.noreply.github.com> Co-authored-by: Rahul Tuli <rtuli@redhat.com> Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Yang Liu <127183760+KKSK-DON@users.noreply.github.com> Co-authored-by: Deboleina <debroy@redhat.com> Co-authored-by: yinz-aizip <yinz@aizip.ai> Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Co-authored-by: wangzi <3220100013@zju.edu.cn> Co-authored-by: Eldar Kurtić <8884008+eldarkurtic@users.noreply.github.com> Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com> Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com> Co-authored-by: Yizhou <136800916+yiz-liu@users.noreply.github.com> Co-authored-by: Sara-KS <50249410+Sara-KS@users.noreply.github.com> Co-authored-by: Csrayz <jover@cmbchina.com> Co-authored-by: ivyilike <pww123@cmbchina.com> Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com> Co-authored-by: Bowen Wang <abmfy@icloud.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com> Co-authored-by: Daisy-Ma-coder <daisy.ma.0117@gmail.com> Co-authored-by: qqma <qqma@amazon.com> Co-authored-by: ElizaWszola <ewszola@redhat.com> Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com> Co-authored-by: Zhuohan Li <zhuohan123@gmail.com> Co-authored-by: Simon Mo <simon.mo@hey.com> Co-authored-by: Or Ozeri <oro@il.ibm.com> Co-authored-by: Johnny Yang <24908445+jcyang43@users.noreply.github.com> Co-authored-by: Chengji Yao <chengjiyao@google.com> Co-authored-by: Alec S <10566873+alecsolder@users.noreply.github.com> Co-authored-by: Alec Solder <alecs@fb.com> Co-authored-by: Russell Bryant <rbryant@redhat.com> Co-authored-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> Co-authored-by: Chris Bamford <chrisbam4d@gmail.com> Co-authored-by: Alexander Matveev <59768536+alexm-redhat@users.noreply.github.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> Co-authored-by: JJJYmmm <92386084+JJJYmmm@users.noreply.github.com> Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com> Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com> Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com> Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com> Co-authored-by: Ming Yang <yming@meta.com> Co-authored-by: Zhikaiiii <55917203+Zhikaiiii@users.noreply.github.com> Co-authored-by: Andreas Hartel <andreas@hartel.me> Co-authored-by: Jee Jee Li <pandaleefree@gmail.com> Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com> Co-authored-by: Joel <wuxibin89@163.com> Co-authored-by: youkaichao <youkaichao@gmail.com> Co-authored-by: Mark McLoughlin <markmc@redhat.com> Co-authored-by: Peter Pan <peter.pan@daocloud.io> Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com> Co-authored-by: Fanli Lin <fanli.lin@intel.com> Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com> Co-authored-by: Sage Moore <sage@neuralmagic.com> Co-authored-by: yewentao256 <zhyanwentao@126.com> Co-authored-by: bnellnm <49004751+bnellnm@users.noreply.github.com> Co-authored-by: rivos-shreeasish <shreeasish@rivosinc.com> Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com> Co-authored-by: Weida Hong <wdhongtw@gmail.com> Co-authored-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com> Co-authored-by: Hashem Hashemi <159079214+amd-hhashemi@users.noreply.github.com> Co-authored-by: Amir Samani <samani@ualberta.ca> Co-authored-by: Luka Govedič <lgovedic@redhat.com> Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com> Co-authored-by: Ilya Markov <markovilya197@gmail.com> Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com> Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Co-authored-by: rouchenzi <40842833+rouchenzi@users.noreply.github.com> Co-authored-by: Andrew Xia <axia@meta.com> Co-authored-by: kourosh hakhamaneshi <31483498+kouroshHakha@users.noreply.github.com> Co-authored-by: Corey Lowman <clowman1993@gmail.com> Co-authored-by: Juan Villamizar <100237675+jpvillam-amd@users.noreply.github.com> Co-authored-by: jpvillam <jpvillam@amd.com> Co-authored-by: Doug Smith <dosmith@redhat.com> Co-authored-by: Chenxi Yang <cxyang@cs.utexas.edu> Co-authored-by: Chenxi Yang <cxyang@fb.com> Co-authored-by: ahao-anyscale <ahao@anyscale.com> Co-authored-by: 0xNullPath <luyanfcp@foxmail.com> Co-authored-by: baxingpiaochong <771405853@qq.com> Co-authored-by: Benjamin Chislett <bchislett@nvidia.com> Co-authored-by: Kyle Sayers <kylesayrs@gmail.com> Co-authored-by: Nikhil Gupta <nikhil.gupta2@arm.com> Co-authored-by: Yong Hoon Shin <48474650+sarckk@users.noreply.github.com> Co-authored-by: lhsjohn <huashuoli@tencent.com> Co-authored-by: Ben Browning <bbrownin@redhat.com> Co-authored-by: Li, Jiang <jiang1.li@intel.com> Co-authored-by: Jackmin801 <56836461+Jackmin801@users.noreply.github.com> Co-authored-by: Jonas M. Kübler <44084297+jmkuebler@users.noreply.github.com> Co-authored-by: Tao Hui <taohui3@gmail.com> Co-authored-by: rongfu.leng <rongfu.leng@daocloud.io> Co-authored-by: Shu Wang <shuw@nvidia.com> Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com> Co-authored-by: Duncan Moss <djm.moss@gmail.com> Co-authored-by: Shiyan Deng <dsy842974287@meta.com> Co-authored-by: Wei Wei <wwei6@meta.com> Co-authored-by: Saman A. Pour <samanamp@outlook.com> Co-authored-by: XuruiYang <530534756@qq.com> Co-authored-by: yangxurui <yangxurui@meituan.com> Co-authored-by: Nicole LiHui 🥜 <nicolelihui@outlook.com> Co-authored-by: courage17340 <courage17340@users.noreply.github.com> Co-authored-by: Jacob Kahn <jacobkahn1@gmail.com> Co-authored-by: Nicole LiHui 🥜 <nicole.li@daocloud.io> Co-authored-by: Fadi Arafeh <115173828+fadara01@users.noreply.github.com> Co-authored-by: Agata Dobrzyniewicz <160237065+adobrzyn@users.noreply.github.com> Co-authored-by: yyzxw <34639446+yyzxw@users.noreply.github.com> Co-authored-by: wang.yuqi <noooop@126.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: chenlang <chen.lang5@zte.com.cn> Co-authored-by: chenlang <10346245@zte.com.cn> Co-authored-by: AlonKejzman <alonkeizman@gmail.com> Co-authored-by: tomeras91 <57313761+tomeras91@users.noreply.github.com> Co-authored-by: Aleksandr Malyshev <164964928+maleksan85@users.noreply.github.com> Co-authored-by: Aleksandr Malyshev <maleksan@amd.com> Co-authored-by: Doug Lehr <douglehr@amd.com> Co-authored-by: Eugene Khvedchenya <ekhvedchenya@gmail.com> Co-authored-by: yitingdc <59356937+yitingdc@users.noreply.github.com> Co-authored-by: xaguilar-amd <xavier.aguilarfruto@amd.com> Co-authored-by: Iceber Gu <caiwei95@hotmail.com> Co-authored-by: Tao He <linzhu.ht@alibaba-inc.com> Co-authored-by: Icey <1790571317@qq.com> Co-authored-by: Xu Wenqing <121550081+Xu-Wenqing@users.noreply.github.com> Co-authored-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com> Co-authored-by: RishiAstra <40644327+RishiAstra@users.noreply.github.com>
312 lines
9.2 KiB
CMake
312 lines
9.2 KiB
CMake
include(FetchContent)
|
|
|
|
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
|
set(CMAKE_CXX_STANDARD 17)
|
|
set(CMAKE_CXX_EXTENSIONS ON)
|
|
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
|
|
|
if (${CMAKE_SYSTEM_NAME} MATCHES "Darwin")
|
|
set(MACOSX_FOUND TRUE)
|
|
endif()
|
|
|
|
|
|
#
|
|
# Define environment variables for special configurations
|
|
#
|
|
set(ENABLE_AVX512BF16 $ENV{VLLM_CPU_AVX512BF16})
|
|
set(ENABLE_AVX512VNNI $ENV{VLLM_CPU_AVX512VNNI})
|
|
|
|
include_directories("${CMAKE_SOURCE_DIR}/csrc")
|
|
|
|
|
|
set (ENABLE_NUMA TRUE)
|
|
|
|
#
|
|
# Check the compile flags
|
|
#
|
|
|
|
if (CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64")
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-mf16c"
|
|
)
|
|
endif()
|
|
|
|
if(MACOSX_FOUND)
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-DVLLM_CPU_EXTENSION")
|
|
else()
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-fopenmp"
|
|
"-DVLLM_CPU_EXTENSION")
|
|
endif()
|
|
|
|
if (NOT MACOSX_FOUND)
|
|
execute_process(COMMAND cat /proc/cpuinfo
|
|
RESULT_VARIABLE CPUINFO_RET
|
|
OUTPUT_VARIABLE CPUINFO)
|
|
if (NOT CPUINFO_RET EQUAL 0)
|
|
message(FATAL_ERROR "Failed to check CPU features via /proc/cpuinfo")
|
|
endif()
|
|
endif()
|
|
|
|
|
|
function (find_isa CPUINFO TARGET OUT)
|
|
string(FIND ${CPUINFO} ${TARGET} ISA_FOUND)
|
|
if(NOT ISA_FOUND EQUAL -1)
|
|
set(${OUT} ON PARENT_SCOPE)
|
|
else()
|
|
set(${OUT} OFF PARENT_SCOPE)
|
|
endif()
|
|
endfunction()
|
|
|
|
|
|
function(check_sysctl TARGET OUT)
|
|
execute_process(COMMAND sysctl -n "${TARGET}"
|
|
RESULT_VARIABLE SYSCTL_RET
|
|
OUTPUT_VARIABLE SYSCTL_INFO
|
|
ERROR_QUIET
|
|
OUTPUT_STRIP_TRAILING_WHITESPACE)
|
|
if(SYSCTL_RET EQUAL 0 AND
|
|
(SYSCTL_INFO STREQUAL "1" OR SYSCTL_INFO GREATER 0))
|
|
set(${OUT} ON PARENT_SCOPE)
|
|
else()
|
|
set(${OUT} OFF PARENT_SCOPE)
|
|
endif()
|
|
endfunction()
|
|
|
|
|
|
function (is_avx512_disabled OUT)
|
|
set(DISABLE_AVX512 $ENV{VLLM_CPU_DISABLE_AVX512})
|
|
if(DISABLE_AVX512 AND DISABLE_AVX512 STREQUAL "true")
|
|
set(${OUT} ON PARENT_SCOPE)
|
|
else()
|
|
set(${OUT} OFF PARENT_SCOPE)
|
|
endif()
|
|
endfunction()
|
|
|
|
is_avx512_disabled(AVX512_DISABLED)
|
|
|
|
if (MACOSX_FOUND AND CMAKE_SYSTEM_PROCESSOR STREQUAL "arm64")
|
|
message(STATUS "Apple Silicon Detected")
|
|
set(APPLE_SILICON_FOUND TRUE)
|
|
set(ENABLE_NUMA OFF)
|
|
check_sysctl(hw.optional.neon ASIMD_FOUND)
|
|
check_sysctl(hw.optional.arm.FEAT_BF16 ARM_BF16_FOUND)
|
|
else()
|
|
find_isa(${CPUINFO} "avx2" AVX2_FOUND)
|
|
find_isa(${CPUINFO} "avx512f" AVX512_FOUND)
|
|
find_isa(${CPUINFO} "Power11" POWER11_FOUND)
|
|
find_isa(${CPUINFO} "POWER10" POWER10_FOUND)
|
|
find_isa(${CPUINFO} "POWER9" POWER9_FOUND)
|
|
find_isa(${CPUINFO} "asimd" ASIMD_FOUND) # Check for ARM NEON support
|
|
find_isa(${CPUINFO} "bf16" ARM_BF16_FOUND) # Check for ARM BF16 support
|
|
find_isa(${CPUINFO} "S390" S390_FOUND)
|
|
find_isa(${CPUINFO} "v" RVV_FOUND) # Check for RISC-V RVV support
|
|
endif()
|
|
|
|
if (AVX512_FOUND AND NOT AVX512_DISABLED)
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-mavx512f"
|
|
"-mavx512vl"
|
|
"-mavx512bw"
|
|
"-mavx512dq")
|
|
|
|
find_isa(${CPUINFO} "avx512_bf16" AVX512BF16_FOUND)
|
|
if (AVX512BF16_FOUND OR ENABLE_AVX512BF16)
|
|
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU" AND
|
|
CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 12.3)
|
|
list(APPEND CXX_COMPILE_FLAGS "-mavx512bf16")
|
|
set(ENABLE_AVX512BF16 ON)
|
|
else()
|
|
set(ENABLE_AVX512BF16 OFF)
|
|
message(WARNING "Disable AVX512-BF16 ISA support, requires gcc/g++ >= 12.3")
|
|
endif()
|
|
else()
|
|
set(ENABLE_AVX512BF16 OFF)
|
|
message(WARNING "Disable AVX512-BF16 ISA support, no avx512_bf16 found in local CPU flags." " If cross-compilation is required, please set env VLLM_CPU_AVX512BF16=1.")
|
|
endif()
|
|
|
|
find_isa(${CPUINFO} "avx512_vnni" AVX512VNNI_FOUND)
|
|
if (AVX512VNNI_FOUND OR ENABLE_AVX512VNNI)
|
|
if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU" AND
|
|
CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 12.3)
|
|
list(APPEND CXX_COMPILE_FLAGS "-mavx512vnni")
|
|
set(ENABLE_AVX512VNNI ON)
|
|
else()
|
|
set(ENABLE_AVX512VNNI OFF)
|
|
message(WARNING "Disable AVX512-VNNI ISA support, requires gcc/g++ >= 12.3")
|
|
endif()
|
|
else()
|
|
set(ENABLE_AVX512VNNI OFF)
|
|
message(WARNING "Disable AVX512-VNNI ISA support, no avx512_vnni found in local CPU flags." " If cross-compilation is required, please set env VLLM_CPU_AVX512VNNI=1.")
|
|
endif()
|
|
|
|
elseif (AVX2_FOUND)
|
|
list(APPEND CXX_COMPILE_FLAGS "-mavx2")
|
|
message(WARNING "vLLM CPU backend using AVX2 ISA")
|
|
|
|
elseif (POWER9_FOUND OR POWER10_FOUND OR POWER11_FOUND)
|
|
message(STATUS "PowerPC detected")
|
|
if (POWER9_FOUND)
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-mvsx"
|
|
"-mcpu=power9"
|
|
"-mtune=power9")
|
|
elseif (POWER10_FOUND OR POWER11_FOUND)
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-mvsx"
|
|
"-mcpu=power10"
|
|
"-mtune=power10")
|
|
endif()
|
|
|
|
elseif (ASIMD_FOUND)
|
|
message(STATUS "ARMv8 or later architecture detected")
|
|
if(ARM_BF16_FOUND)
|
|
message(STATUS "BF16 extension detected")
|
|
set(MARCH_FLAGS "-march=armv8.2-a+bf16+dotprod+fp16")
|
|
add_compile_definitions(ARM_BF16_SUPPORT)
|
|
else()
|
|
message(WARNING "BF16 functionality is not available")
|
|
set(MARCH_FLAGS "-march=armv8.2-a+dotprod+fp16")
|
|
endif()
|
|
list(APPEND CXX_COMPILE_FLAGS ${MARCH_FLAGS})
|
|
elseif (S390_FOUND)
|
|
message(STATUS "S390 detected")
|
|
# Check for S390 VXE support
|
|
list(APPEND CXX_COMPILE_FLAGS
|
|
"-mvx"
|
|
"-mzvector"
|
|
"-march=native"
|
|
"-mtune=native")
|
|
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "riscv64")
|
|
if(RVV_FOUND)
|
|
message(FAIL_ERROR "Can't support rvv now.")
|
|
else()
|
|
list(APPEND CXX_COMPILE_FLAGS "-march=rv64gc")
|
|
endif()
|
|
else()
|
|
message(FATAL_ERROR "vLLM CPU backend requires AVX512, AVX2, Power9+ ISA, S390X ISA, ARMv8 or RISC-V support.")
|
|
endif()
|
|
|
|
#
|
|
# Build oneDNN for W8A8 GEMM kernels (only for x86-AVX512 /ARM platforms)
|
|
# Flag to enable ACL kernels for AARCH64 platforms
|
|
if (VLLM_BUILD_ACL STREQUAL "ON")
|
|
set(USE_ACL ON)
|
|
else()
|
|
set(USE_ACL OFF)
|
|
endif()
|
|
|
|
if ((AVX512_FOUND AND NOT AVX512_DISABLED) OR (ASIMD_FOUND AND NOT APPLE_SILICON_FOUND) OR POWER9_FOUND OR POWER10_FOUND OR POWER11_FOUND)
|
|
FetchContent_Declare(
|
|
oneDNN
|
|
GIT_REPOSITORY https://github.com/oneapi-src/oneDNN.git
|
|
GIT_TAG v3.9
|
|
GIT_PROGRESS TRUE
|
|
GIT_SHALLOW TRUE
|
|
)
|
|
|
|
if(USE_ACL)
|
|
find_library(ARM_COMPUTE_LIBRARY NAMES arm_compute PATHS $ENV{ACL_ROOT_DIR}/build/)
|
|
if(NOT ARM_COMPUTE_LIBRARY)
|
|
message(FATAL_ERROR "Could not find ARM Compute Library: please set ACL_ROOT_DIR")
|
|
endif()
|
|
set(ONEDNN_AARCH64_USE_ACL "ON")
|
|
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wl,-rpath,$ENV{ACL_ROOT_DIR}/build/")
|
|
endif()
|
|
|
|
set(ONEDNN_LIBRARY_TYPE "STATIC")
|
|
set(ONEDNN_BUILD_DOC "OFF")
|
|
set(ONEDNN_BUILD_EXAMPLES "OFF")
|
|
set(ONEDNN_BUILD_TESTS "OFF")
|
|
set(ONEDNN_ENABLE_WORKLOAD "INFERENCE")
|
|
set(ONEDNN_ENABLE_PRIMITIVE "MATMUL;REORDER")
|
|
set(ONEDNN_BUILD_GRAPH "OFF")
|
|
set(ONEDNN_ENABLE_JIT_PROFILING "OFF")
|
|
set(ONEDNN_ENABLE_ITT_TASKS "OFF")
|
|
set(ONEDNN_ENABLE_MAX_CPU_ISA "OFF")
|
|
set(ONEDNN_ENABLE_CPU_ISA_HINTS "OFF")
|
|
set(ONEDNN_VERBOSE "OFF")
|
|
set(CMAKE_POLICY_DEFAULT_CMP0077 NEW)
|
|
|
|
FetchContent_MakeAvailable(oneDNN)
|
|
add_library(dnnl_ext OBJECT "csrc/cpu/dnnl_helper.cpp")
|
|
target_include_directories(
|
|
dnnl_ext
|
|
PUBLIC ${oneDNN_SOURCE_DIR}/include
|
|
PUBLIC ${oneDNN_BINARY_DIR}/include
|
|
PRIVATE ${oneDNN_SOURCE_DIR}/src
|
|
)
|
|
target_link_libraries(dnnl_ext dnnl)
|
|
target_compile_options(dnnl_ext PRIVATE ${CXX_COMPILE_FLAGS} -fPIC)
|
|
list(APPEND LIBS dnnl_ext)
|
|
set(USE_ONEDNN ON)
|
|
else()
|
|
set(USE_ONEDNN OFF)
|
|
endif()
|
|
|
|
message(STATUS "CPU extension compile flags: ${CXX_COMPILE_FLAGS}")
|
|
|
|
if(ENABLE_NUMA)
|
|
list(APPEND LIBS numa)
|
|
else()
|
|
message(STATUS "NUMA is disabled")
|
|
add_compile_definitions(-DVLLM_NUMA_DISABLED)
|
|
endif()
|
|
|
|
#
|
|
# _C extension
|
|
#
|
|
set(VLLM_EXT_SRC
|
|
"csrc/cpu/activation.cpp"
|
|
"csrc/cpu/attention.cpp"
|
|
"csrc/cpu/cache.cpp"
|
|
"csrc/cpu/utils.cpp"
|
|
"csrc/cpu/layernorm.cpp"
|
|
"csrc/cpu/mla_decode.cpp"
|
|
"csrc/cpu/pos_encoding.cpp"
|
|
"csrc/cpu/torch_bindings.cpp"
|
|
"csrc/moe/dynamic_4bit_int_moe_cpu.cpp")
|
|
|
|
if (AVX512_FOUND AND NOT AVX512_DISABLED)
|
|
set(VLLM_EXT_SRC
|
|
"csrc/cpu/shm.cpp"
|
|
${VLLM_EXT_SRC})
|
|
if (ENABLE_AVX512BF16 AND ENABLE_AVX512VNNI)
|
|
set(VLLM_EXT_SRC
|
|
"csrc/cpu/sgl-kernels/gemm.cpp"
|
|
"csrc/cpu/sgl-kernels/gemm_int8.cpp"
|
|
"csrc/cpu/sgl-kernels/gemm_fp8.cpp"
|
|
"csrc/cpu/sgl-kernels/moe.cpp"
|
|
"csrc/cpu/sgl-kernels/moe_int8.cpp"
|
|
"csrc/cpu/sgl-kernels/moe_fp8.cpp"
|
|
${VLLM_EXT_SRC})
|
|
add_compile_definitions(-DCPU_CAPABILITY_AVX512)
|
|
endif()
|
|
endif()
|
|
|
|
if(USE_ONEDNN)
|
|
set(VLLM_EXT_SRC
|
|
"csrc/cpu/dnnl_kernels.cpp"
|
|
${VLLM_EXT_SRC})
|
|
endif()
|
|
|
|
message(STATUS "CPU extension source files: ${VLLM_EXT_SRC}")
|
|
|
|
#
|
|
# Define extension targets
|
|
#
|
|
|
|
define_gpu_extension_target(
|
|
_C
|
|
DESTINATION vllm
|
|
LANGUAGE CXX
|
|
SOURCES ${VLLM_EXT_SRC}
|
|
LIBRARIES ${LIBS}
|
|
COMPILE_FLAGS ${CXX_COMPILE_FLAGS}
|
|
USE_SABI 3
|
|
WITH_SOABI
|
|
)
|
|
|
|
message(STATUS "Enabling C extension.")
|