你指的是图中的这个嗎
按照glmPD分离手册的步骤执行的,执行前容器中进行了网卡驱动的安装,安装了deepep,并且替换了mxshmem库和头文件。使用的镜像为sglang:0.5.10-maca.ai3.7.1.12-torch2.8-py310-ubuntu22.04-amd64
prefill节点可以正常启动,prefill主节点正常回显 The server is fired up and ready to roll!
但是启动decode节点出现上面decode日志中的报错,尝试关闭decode的cuda_graph还是不行
已经装过了,启动decode,在cuda graph阶段报错,报错如文件
用的是博通的网卡,日志中的报错为:
ibgda_mlx5.cpp:2310: non-zero status: -2 mlx5_devices_init failed
→ mxshmem_ibgda_init failed
→ mxshmemi_transport_init failed
→ mxshmem_internal_init_thread failed
是不是和这个有关系,还是要升级网卡版本?
我在六机上进行glm5.1 PD分离操作,启动decode节点报错,报错内容如文件
手册中decode节点是4个,我的意思是decode来两个可以吗?还是必须要按照手册中的节点数去配置
如标题,glm5.1-w8a8做PD分离,decode节点最少需要几个?
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$ sudo dmesg -T | grep -i err
[Wed Jun 17 09:41:06 2026] pmd_set_huge: Cannot satisfy [mem 0x80000000-0x80200000] with a huge-page mapping due to MTRR override.
[Wed Jun 17 09:41:07 2026] ACPI: Using IOAPIC for interrupt routing
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKA configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKA disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKB configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKB disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKC configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKC disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKD configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKD disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKE configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKE disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKF configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKF disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKG configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKG disabled
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKH configured for IRQ 15
[Wed Jun 17 09:41:08 2026] ACPI: PCI: Interrupt link LNKH disabled
[Wed Jun 17 09:41:08 2026] pcieport 0000:15:01.0: pciehp: Slot #20 AttnBtn+ PwrCtrl+ MRL- AttnInd+ PwrInd+ HotPlug+ Surprise- Interlock- NoCompl- IbPresDis- LLActRep+ (with Cmd Compl erratum)
[Wed Jun 17 09:41:08 2026] ERST: Error Record Serialization Table (ERST) support is initialized.
[Wed Jun 17 09:41:10 2026] RAS: Correctable Errors collector initialized.
[Wed Jun 17 09:41:11 2026] i801_smbus 0000:00:1f.4: SMBus using PCI interrupt
[Wed Jun 17 09:41:56 2026] EDAC MC0: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#0: DEV 0000:7e:0c.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC1: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#1: DEV 0000:7e:0d.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC2: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#2: DEV 0000:7e:0e.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC3: Giving out device to module i10nm_edac controller Intel_10nm Socket#0 IMC#3: DEV 0000:7e:0f.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC4: Giving out device to module i10nm_edac controller Intel_10nm Socket#1 IMC#0: DEV 0000:fe:0c.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC5: Giving out device to module i10nm_edac controller Intel_10nm Socket#1 IMC#1: DEV 0000:fe:0d.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC6: Giving out device to module i10nm_edac controller Intel_10nm Socket#1 IMC#2: DEV 0000:fe:0e.0 (INTERRUPT)
[Wed Jun 17 09:41:56 2026] EDAC MC7: Giving out device to module i10nm_edac controller Intel_10nm Socket#1 IMC#3: DEV 0000:fe:0f.0 (INTERRUPT)
[Wed Jun 17 09:41:58 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:41:58 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:41:59 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:41:59 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:01 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:01 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:02 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:02 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:08 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0xc1} len:0
[Wed Jun 17 09:42:13 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0xc2} len:0
[Wed Jun 17 09:42:22 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x27 0x199} len:0
[Wed Jun 17 09:42:28 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x27 0x19a} len:0
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:109c:7fff:fe12:f56d error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:4cbb:66ff:feb7:d4be error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1f02 error=-5
[Wed Jun 17 09:42:30 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1f02 error=-5
[Wed Jun 17 09:42:37 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1b7} len:0
[Wed Jun 17 09:42:42 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x16 0x1b8} len:0
[Wed Jun 17 09:42:51 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1c3} len:0
[Wed Jun 17 09:42:56 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x1c4} len:0
[Wed Jun 17 09:43:06 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1d1} len:0
[Wed Jun 17 09:43:12 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x1d2} len:0
[Wed Jun 17 09:43:21 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1da} len:0
[Wed Jun 17 09:43:26 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x1db} len:0
[Wed Jun 17 09:43:36 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1e9} len:0
[Wed Jun 17 09:43:42 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x1ea} len:0
[Wed Jun 17 09:43:51 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x1f7} len:0
[Wed Jun 17 09:43:56 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x1f8} len:0
[Wed Jun 17 09:44:05 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x200} len:0
[Wed Jun 17 09:44:10 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x201} len:0
[Wed Jun 17 09:44:20 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x20e} len:0
[Wed Jun 17 09:44:26 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x20f} len:0
[Wed Jun 17 09:44:35 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x217} len:0
[Wed Jun 17 09:44:40 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x53 0x218} len:0
[Wed Jun 17 09:44:50 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x227} len:0
[Wed Jun 17 09:44:55 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x228} len:0
[Wed Jun 17 09:45:05 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x5e3} len:0
[Wed Jun 17 09:45:10 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x5e4} len:0
[Wed Jun 17 09:45:19 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x5ec} len:0
[Wed Jun 17 09:45:24 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x5ed} len:0
[Wed Jun 17 09:45:34 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x5fa} len:0
[Wed Jun 17 09:45:40 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x5fb} len:0
[Wed Jun 17 09:45:49 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x608} len:0
[Wed Jun 17 09:45:54 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x609} len:0
[Wed Jun 17 09:46:03 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x612} len:0
[Wed Jun 17 09:46:08 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x613} len:0
[Wed Jun 17 09:46:18 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x620} len:0
[Wed Jun 17 09:46:24 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x621} len:0
[Wed Jun 17 09:46:33 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x629} len:0
[Wed Jun 17 09:46:38 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x62a} len:0
[Wed Jun 17 09:46:48 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x637} len:0
[Wed Jun 17 09:46:54 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x638} len:0
[Wed Jun 17 09:47:02 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x640} len:0
[Wed Jun 17 09:47:08 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x53 0x641} len:0
[Wed Jun 17 09:47:18 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x650} len:0
[Wed Jun 17 09:47:23 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x651} len:0
[Wed Jun 17 09:47:32 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x65e} len:0
[Wed Jun 17 09:47:38 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x65f} len:0
[Wed Jun 17 09:47:46 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x667} len:0
[Wed Jun 17 09:47:52 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x668} len:0
[Wed Jun 17 09:48:02 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x675} len:0
[Wed Jun 17 09:48:07 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0xb4 0x676} len:0
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1d02 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1d02 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:10 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:7ce6:d3ff:febc:45c9 error=-5
[Wed Jun 17 09:48:11 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:11 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1c02 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid 0000:0000:0000:0000:0000:ffff:0a03:1c02 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:12 2026] __ib_cache_gid_add: unable to add gid fe80:0000:0000:0000:200d:68ff:fe64:0385 error=-5
[Wed Jun 17 09:48:16 2026] bnxt_en 0000:4b:00.1 ens13f1np1: Error (timeout: 3000015) msg {0x23 0x688} len:0
[Wed Jun 17 09:48:17 2026] bnxt_en 0000:4b:00.0 ens13f0np0: Error (timeout: 3000015) msg {0x24 0x271} len:0
[Wed Jun 17 09:48:18 2026] bnxt_en 0000:29:00.1 ens11f1np1: Error (timeout: 3000015) msg {0x23 0x2b5} len:0
[Wed Jun 17 09:48:18 2026] bnxt_en 0000:29:00.0 ens11f0np0: Error (timeout: 3000015) msg {0x24 0x2ff} len:0
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$ bash mccl.sh 8
The test is all_reduce_perf, the maca version is /opt/maca-3.7.1
main_process = 7324
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7325: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7326: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7327: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7328: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7329: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7330: Test failure common.cu:1271
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7331: Test failure common.cu:1271
===============================
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7324: Test failure common.cu:1271
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:
Process name: [[25858,1],4]
Exit code: 2
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$ bash mccl.sh 2
The test is all_reduce_perf, the maca version is /opt/maca-3.7.1
main_process = 7378
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7379: Test failure common.cu:1271
===============================
metax-host-104: Test CUDA failure common.cu:1349 'initialization error'
.. metax-host-104 pid 7378: Test failure common.cu:1271
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:
Process name: [[25940,1],0]
Exit code: 2
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$
单机mccl测试失败是怎么回事
mx-smi回显信息正常如下
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$ mx-smi
mx-smi version: 2.3.1
=================== MetaX System Management Interface Log ===================
Timestamp : Wed Jun 17 10:13:47 2026
Attached GPUs : 8
+---------------------------------------------------------------------------------+
| MX-SMI 2.3.1 Kernel Mode Driver Version: 3.8.1 |
| MACA Version: 3.7.1.5 BIOS Version: 1.29.1.0 |
|------------------+-----------------+---------------------+----------------------|
| Board Name | GPU Persist-M | Bus-id | GPU-Util sGPU-M |
| Pwr:Usage/Cap | Temp Perf | Memory-Usage | GPU-State |
|==================+=================+=====================+======================|
| 0 MetaX C550 | 0 Off | 0000:2b:00.0 | 0% Disabled |
| 54W / 450W | 32C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 1 MetaX C550 | 1 Off | 0000:3a:00.0 | 0% Disabled |
| 56W / 450W | 33C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 2 MetaX C550 | 2 Off | 0000:4d:00.0 | 0% Disabled |
| 52W / 450W | 33C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 3 MetaX C550 | 3 Off | 0000:5c:00.0 | 0% Disabled |
| 56W / 450W | 33C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 4 MetaX C550 | 4 Off | 0000:aa:00.0 | 0% Disabled |
| 53W / 450W | 32C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 5 MetaX C550 | 5 Off | 0000:ba:00.0 | 0% Disabled |
| 52W / 450W | 33C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 6 MetaX C550 | 6 Off | 0000:ca:00.0 | 0% Disabled |
| 54W / 450W | 34C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
| 7 MetaX C550 | 7 Off | 0000:da:00.0 | 0% Disabled |
| 53W / 450W | 33C P0 | 858/65536 MiB | Available |
+------------------+-----------------+---------------------+----------------------+
+---------------------------------------------------------------------------------+
| Process: |
| GPU PID Process Name GPU Memory |
| Usage(MiB) |
|=================================================================================|
| no process found |
+---------------------------------------------------------------------------------+
End of Log
metax@metax-host-104:/opt/maca/samples/mccl_tests/perf$
我看手册中有这样的内容:sGPU设备实例不支持互连功能,互连功能包括PCle P2P和MetaXLink,服务器不是一般会安装metaxlink吗,这个不会影响模型推理性能吗