github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15131] is it possibel to run both m60 gpus in linux? #9687

New Issue
Open
opened 2026-04-12 22:34:09 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 22:34:09 -05:00
Owner
Copy Link

Originally created by @jcharth on GitHub (Mar 29, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15131

What is the issue?

I picked up a m60 on ebay. gpu 0 can only run in vulkan mode with no cuda version specified. gpu 1 can run on vulkan with cuda version 12 specified but i can also run without vulkan. i can run 2 instances of ollama with different settings. i tried cuda 11. i tried multiple driver versions and cuda versions. i also tried multiple ollama versions. ive seen posts of people running 1 gpu only in the m60 testla gpu. i also tried snapd and docker with no luck. memtest_vulkan runs fine on both gpus. any suggestions. thanks.

Relevant log output

CUDA error: an illegal memory access was encountered
  current device: 0, in function ggml_backend_cuda_synchronize at /ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2981
  cudaStreamSynchronize(cuda_ctx->stream())

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.18.3

Originally created by @jcharth on GitHub (Mar 29, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15131 ### What is the issue? I picked up a m60 on ebay. gpu 0 can only run in vulkan mode with no cuda version specified. gpu 1 can run on vulkan with cuda version 12 specified but i can also run without vulkan. i can run 2 instances of ollama with different settings. i tried cuda 11. i tried multiple driver versions and cuda versions. i also tried multiple ollama versions. ive seen posts of people running 1 gpu only in the m60 testla gpu. i also tried snapd and docker with no luck. memtest_vulkan runs fine on both gpus. any suggestions. thanks. ### Relevant log output ```shell CUDA error: an illegal memory access was encountered current device: 0, in function ggml_backend_cuda_synchronize at /ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2981 cudaStreamSynchronize(cuda_ctx->stream()) ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.18.3
GiteaMirror added the bug label 2026-04-12 22:34:09 -05:00
GiteaMirror commented 2026-04-12 22:34:10 -05:00
Author
Owner
Copy Link

@Profex86 commented on GitHub (Mar 29, 2026):

One of the two M60 dies is still in Graphics‑Only mode or in a “vGPU‑locked” profile. both "GPUs" must be run in Compute mode, GOM = 0.

GPU 0
nvidia-smi -q -i 0

GPU 1
nvidia-smi -q -i 1

Mismatch?

0 = Compute, 1 = Graphics
sudo nvidia-smi -i 0 -gom 0
sudo nvidia-smi -i 1 -gom 0

Check
nvidia-smi -q -i 0 | grep GOM
nvidia-smi -i

vGPU Profile ?
sudo nvidia-smi -i 0 -vgpu-unload

BAR size the same?
e.g
128 MiB <-- GPU 0
256 MiB <-- GPU 1

Different cap. report?

deviceQuery -device=0
deviceQuery -device=1

reset
sudo nvidia-smi --gpu-reset -i 0
sudo nvidia-smi --gpu-reset -i 1

<!-- gh-comment-id:4150564813 --> @Profex86 commented on GitHub (Mar 29, 2026): One of the two M60 dies is still in Graphics‑Only mode or in a “vGPU‑locked” profile. both "GPUs" must be run in Compute mode, GOM = 0. GPU 0 nvidia-smi -q -i 0 GPU 1 nvidia-smi -q -i 1 Mismatch? 0 = Compute, 1 = Graphics sudo nvidia-smi -i 0 -gom 0 sudo nvidia-smi -i 1 -gom 0 Check nvidia-smi -q -i 0 | grep GOM nvidia-smi -i vGPU Profile ? sudo nvidia-smi -i 0 -vgpu-unload BAR size the same? e.g 128 MiB <-- GPU 0 256 MiB <-- GPU 1 Different cap. report? deviceQuery -device=0 deviceQuery -device=1 reset sudo nvidia-smi --gpu-reset -i 0 sudo nvidia-smi --gpu-reset -i 1
GiteaMirror commented 2026-04-12 22:34:11 -05:00
Author
Owner
Copy Link

@jcharth commented on GitHub (Mar 29, 2026):

thanks gom does not work with mine. i tried reset gpu 0 and it froze.
i had tried using sudo nvidia-smi -g 0 --compute-mode=3 and
sudo nvidia-smi -g 0 --compute-mode=0

here is the output. may be it is helpful

nvidia-smi -q -i 1

==============NVSMI LOG==============

Timestamp : Sun Mar 29 13:37:12 2026
Driver Version : 560.35.05
CUDA Version : 12.6

Attached GPUs : 2
GPU 00000000:04:00.0
Product Name : Tesla M60
Product Brand : Tesla
Product Architecture : Maxwell
Display Mode : Disabled
Display Active : Disabled
Persistence Mode : Enabled
Addressing Mode : N/A
MIG Mode
Current : N/A
Pending : N/A
Accounting Mode : Disabled
Accounting Mode Buffer Size : 4000
Driver Model
Current : N/A
Pending : N/A
Serial Number : 0325017235045
GPU UUID : GPU-5e87152d-a86a-372d-af09-41191a29f8a1
Minor Number : 1
VBIOS Version : 84.04.9F.00.14
MultiGPU Board : Yes
Board ID : 0x100
Board Part Number : 900-2G402-0310-030
GPU Part Number : 13F2-895-A1
FRU Part Number : N/A
Module ID : 1
Inforom Version
Image Version : G402.0060.00.04
OEM Object : 1.1
ECC Object : 3.0
Power Management Object : N/A
Inforom BBX Object Flush
Latest Timestamp : N/A
Latest Duration : N/A
GPU Operation Mode
Current : N/A
Pending : N/A
GPU C2C Mode : N/A
GPU Virtualization Mode
Virtualization Mode : None
Host VGPU Mode : N/A
vGPU Heterogeneous Mode : N/A
GPU Reset Status
Reset Required : N/A
Drain and Reset Recommended : N/A
GSP Firmware Version : N/A
IBMNPU
Relaxed Ordering Mode : N/A
PCI
Bus : 0x04
Device : 0x00
Domain : 0x0000
Base Classcode : 0x3
Sub Classcode : 0x0
Device Id : 0x13F210DE
Bus Id : 00000000:04:00.0
Sub System Id : 0x115E10DE
GPU Link Info
PCIe Generation
Max : 3
Current : 1
Device Current : 1
Device Max : 3
Host Max : 3
Link Width
Max : 16x
Current : 16x
Bridge Chip
Type : N/A
Firmware : N/A
Replays Since Reset : 0
Replay Number Rollovers : 0
Tx Throughput : 0 KB/s
Rx Throughput : 0 KB/s
Atomic Caps Outbound : N/A
Atomic Caps Inbound : N/A
Fan Speed : N/A
Performance State : P8
Clocks Event Reasons
Idle : Active
Applications Clocks Setting : Not Active
SW Power Cap : Not Active
HW Slowdown : Not Active
HW Thermal Slowdown : N/A
HW Power Brake Slowdown : N/A
Sync Boost : Not Active
SW Thermal Slowdown : Not Active
Display Clock Setting : Not Active
Sparse Operation Mode : N/A
FB Memory Usage
Total : 8192 MiB
Reserved : 76 MiB
Used : 0 MiB
Free : 8117 MiB
BAR1 Memory Usage
Total : 256 MiB
Used : 2 MiB
Free : 254 MiB
Conf Compute Protected Memory Usage
Total : 0 MiB
Used : 0 MiB
Free : 0 MiB
Compute Mode : Default
Utilization
Gpu : 0 %
Memory : 0 %
Encoder : 0 %
Decoder : 0 %
JPEG : N/A
OFA : N/A
Encoder Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
FBC Stats
Active Sessions : 0
Average FPS : 0
Average Latency : 0
ECC Mode
Current : Disabled
Pending : Disabled
ECC Errors
Volatile
Single Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : N/A
Double Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : N/A
Aggregate
Single Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : N/A
Double Bit
Device Memory : N/A
Register File : N/A
L1 Cache : N/A
L2 Cache : N/A
Texture Memory : N/A
Texture Shared : N/A
CBU : N/A
Total : N/A
Retired Pages
Single Bit ECC : 0
Double Bit ECC : 1
Pending Page Blacklist : No
Remapped Rows : N/A
Temperature
GPU Current Temp : 25 C
GPU T.Limit Temp : N/A
GPU Shutdown Temp : 91 C
GPU Slowdown Temp : 88 C
GPU Max Operating Temp : N/A
GPU Target Temperature : 85 C
Memory Current Temp : N/A
Memory Max Operating Temp : N/A
GPU Power Readings
Power Draw : 15.71 W
Current Power Limit : 150.00 W
Requested Power Limit : 150.00 W
Default Power Limit : 150.00 W
Min Power Limit : 112.50 W
Max Power Limit : 162.00 W
GPU Memory Power Readings
Power Draw : N/A
Module Power Readings
Power Draw : N/A
Current Power Limit : N/A
Requested Power Limit : N/A
Default Power Limit : N/A
Min Power Limit : N/A
Max Power Limit : N/A
Clocks
Graphics : 405 MHz
SM : 405 MHz
Memory : 324 MHz
Video : 405 MHz
Applications Clocks
Graphics : 557 MHz
Memory : 2505 MHz
Default Applications Clocks
Graphics : 557 MHz
Memory : 2505 MHz
Deferred Clocks
Memory : N/A
Max Clocks
Graphics : 1177 MHz
SM : 1177 MHz
Memory : 2505 MHz
Video : 1083 MHz
Max Customer Boost Clocks
Graphics : N/A
Clock Policy
Auto Boost : On
Auto Boost Default : On
Voltage
Graphics : N/A
Fabric
State : N/A
Status : N/A
CliqueId : N/A
ClusterUUID : N/A
Health
Bandwidth : N/A
Processes : None
Capabilities
EGM : disabled

<!-- gh-comment-id:4150682717 --> @jcharth commented on GitHub (Mar 29, 2026): thanks gom does not work with mine. i tried reset gpu 0 and it froze. i had tried using sudo nvidia-smi -g 0 --compute-mode=3 and sudo nvidia-smi -g 0 --compute-mode=0 here is the output. may be it is helpful nvidia-smi -q -i 1 ==============NVSMI LOG============== Timestamp : Sun Mar 29 13:37:12 2026 Driver Version : 560.35.05 CUDA Version : 12.6 Attached GPUs : 2 GPU 00000000:04:00.0 Product Name : Tesla M60 Product Brand : Tesla Product Architecture : Maxwell Display Mode : Disabled Display Active : Disabled Persistence Mode : Enabled Addressing Mode : N/A MIG Mode Current : N/A Pending : N/A Accounting Mode : Disabled Accounting Mode Buffer Size : 4000 Driver Model Current : N/A Pending : N/A Serial Number : 0325017235045 GPU UUID : GPU-5e87152d-a86a-372d-af09-41191a29f8a1 Minor Number : 1 VBIOS Version : 84.04.9F.00.14 MultiGPU Board : Yes Board ID : 0x100 Board Part Number : 900-2G402-0310-030 GPU Part Number : 13F2-895-A1 FRU Part Number : N/A Module ID : 1 Inforom Version Image Version : G402.0060.00.04 OEM Object : 1.1 ECC Object : 3.0 Power Management Object : N/A Inforom BBX Object Flush Latest Timestamp : N/A Latest Duration : N/A GPU Operation Mode Current : N/A Pending : N/A GPU C2C Mode : N/A GPU Virtualization Mode Virtualization Mode : None Host VGPU Mode : N/A vGPU Heterogeneous Mode : N/A GPU Reset Status Reset Required : N/A Drain and Reset Recommended : N/A GSP Firmware Version : N/A IBMNPU Relaxed Ordering Mode : N/A PCI Bus : 0x04 Device : 0x00 Domain : 0x0000 Base Classcode : 0x3 Sub Classcode : 0x0 Device Id : 0x13F210DE Bus Id : 00000000:04:00.0 Sub System Id : 0x115E10DE GPU Link Info PCIe Generation Max : 3 Current : 1 Device Current : 1 Device Max : 3 Host Max : 3 Link Width Max : 16x Current : 16x Bridge Chip Type : N/A Firmware : N/A Replays Since Reset : 0 Replay Number Rollovers : 0 Tx Throughput : 0 KB/s Rx Throughput : 0 KB/s Atomic Caps Outbound : N/A Atomic Caps Inbound : N/A Fan Speed : N/A Performance State : P8 Clocks Event Reasons Idle : Active Applications Clocks Setting : Not Active SW Power Cap : Not Active HW Slowdown : Not Active HW Thermal Slowdown : N/A HW Power Brake Slowdown : N/A Sync Boost : Not Active SW Thermal Slowdown : Not Active Display Clock Setting : Not Active Sparse Operation Mode : N/A FB Memory Usage Total : 8192 MiB Reserved : 76 MiB Used : 0 MiB Free : 8117 MiB BAR1 Memory Usage Total : 256 MiB Used : 2 MiB Free : 254 MiB Conf Compute Protected Memory Usage Total : 0 MiB Used : 0 MiB Free : 0 MiB Compute Mode : Default Utilization Gpu : 0 % Memory : 0 % Encoder : 0 % Decoder : 0 % JPEG : N/A OFA : N/A Encoder Stats Active Sessions : 0 Average FPS : 0 Average Latency : 0 FBC Stats Active Sessions : 0 Average FPS : 0 Average Latency : 0 ECC Mode Current : Disabled Pending : Disabled ECC Errors Volatile Single Bit Device Memory : N/A Register File : N/A L1 Cache : N/A L2 Cache : N/A Texture Memory : N/A Texture Shared : N/A CBU : N/A Total : N/A Double Bit Device Memory : N/A Register File : N/A L1 Cache : N/A L2 Cache : N/A Texture Memory : N/A Texture Shared : N/A CBU : N/A Total : N/A Aggregate Single Bit Device Memory : N/A Register File : N/A L1 Cache : N/A L2 Cache : N/A Texture Memory : N/A Texture Shared : N/A CBU : N/A Total : N/A Double Bit Device Memory : N/A Register File : N/A L1 Cache : N/A L2 Cache : N/A Texture Memory : N/A Texture Shared : N/A CBU : N/A Total : N/A Retired Pages Single Bit ECC : 0 Double Bit ECC : 1 Pending Page Blacklist : No Remapped Rows : N/A Temperature GPU Current Temp : 25 C GPU T.Limit Temp : N/A GPU Shutdown Temp : 91 C GPU Slowdown Temp : 88 C GPU Max Operating Temp : N/A GPU Target Temperature : 85 C Memory Current Temp : N/A Memory Max Operating Temp : N/A GPU Power Readings Power Draw : 15.71 W Current Power Limit : 150.00 W Requested Power Limit : 150.00 W Default Power Limit : 150.00 W Min Power Limit : 112.50 W Max Power Limit : 162.00 W GPU Memory Power Readings Power Draw : N/A Module Power Readings Power Draw : N/A Current Power Limit : N/A Requested Power Limit : N/A Default Power Limit : N/A Min Power Limit : N/A Max Power Limit : N/A Clocks Graphics : 405 MHz SM : 405 MHz Memory : 324 MHz Video : 405 MHz Applications Clocks Graphics : 557 MHz Memory : 2505 MHz Default Applications Clocks Graphics : 557 MHz Memory : 2505 MHz Deferred Clocks Memory : N/A Max Clocks Graphics : 1177 MHz SM : 1177 MHz Memory : 2505 MHz Video : 1083 MHz Max Customer Boost Clocks Graphics : N/A Clock Policy Auto Boost : On Auto Boost Default : On Voltage Graphics : N/A Fabric State : N/A Status : N/A CliqueId : N/A ClusterUUID : N/A Health Bandwidth : N/A Processes : None Capabilities EGM : disabled
GiteaMirror commented 2026-04-12 22:34:11 -05:00
Author
Owner
Copy Link

@jcharth commented on GitHub (Mar 29, 2026):

i just tried

sudo nvidia-smi -i 0 -c EXCLUSIVE_PROCESS
sudo nvidia-smi -i 1 -c EXCLUSIVE_PROCESS

but same result.

<!-- gh-comment-id:4150892290 --> @jcharth commented on GitHub (Mar 29, 2026): i just tried sudo nvidia-smi -i 0 -c EXCLUSIVE_PROCESS sudo nvidia-smi -i 1 -c EXCLUSIVE_PROCESS but same result.
GiteaMirror commented 2026-04-12 22:34:12 -05:00
Author
Owner
Copy Link

@Profex86 commented on GitHub (Mar 29, 2026):

check_m60.sh, make it executable
(chmod +x check_m60.sh) and run it. It prints the fields we care about for
both devices in a compact form.

``
#!/bin/bash
for i in 0 1; do
echo "=== GPU $i ==="
nvidia-smi -q -i $i | awk '
/GOM/ {print "GOM:", $3}
/vGPU/ && !/Profile/ {print "vGPU:", $2}
/vGPU Profile/ {print "vGPU Profile:", $3}
/Total/ && /BAR1/ {print "BAR1 Total:", $3, $4}
/ECC Mode/ {print "ECC:", $3}
/Perf State/ {print "PerfState:", $3}
/Supported CUDA Version/ {print "CUDAver:", $4}
/Graphics Clock/ {print "GraphicsClk:", $3, $4}
/SM Clock/ {print "SMClk:", $3, $4}
/Memory Clock/ {print "MemClk:", $3, $4}
/UUID/ {print "UUID:", $2}
/Bus Id/ {print "BusId:", $3}
'
echo
done

``

<!-- gh-comment-id:4151068803 --> @Profex86 commented on GitHub (Mar 29, 2026): check_m60.sh, make it executable (chmod +x check_m60.sh) and run it. It prints the fields we care about for both devices in a compact form. `` #!/bin/bash for i in 0 1; do echo "=== GPU $i ===" nvidia-smi -q -i $i | awk ' /GOM/ {print "GOM:", $3} /vGPU/ && !/Profile/ {print "vGPU:", $2} /vGPU Profile/ {print "vGPU Profile:", $3} /Total/ && /BAR1/ {print "BAR1 Total:", $3, $4} /ECC Mode/ {print "ECC:", $3} /Perf State/ {print "PerfState:", $3} /Supported CUDA Version/ {print "CUDAver:", $4} /Graphics Clock/ {print "GraphicsClk:", $3, $4} /SM Clock/ {print "SMClk:", $3, $4} /Memory Clock/ {print "MemClk:", $3, $4} /UUID/ {print "UUID:", $2} /Bus Id/ {print "BusId:", $3} ' echo done ``
GiteaMirror commented 2026-04-12 22:34:12 -05:00
Author
Owner
Copy Link

@Profex86 commented on GitHub (Mar 29, 2026):

i see
Single Bit ECC : 0
Double Bit ECC: 1 <----- not great... trying to identify the issue, but no need to panic. I believe this isn’t a hardware fault. I think it’s a routing problem, concurrency, or similar issues, maybe the BIOS handles it as two dedicated GPUs and the other stuff.

<!-- gh-comment-id:4151098673 --> @Profex86 commented on GitHub (Mar 29, 2026): i see Single Bit ECC : 0 Double Bit ECC: 1 <----- not great... trying to identify the issue, but no need to panic. I believe this isn’t a hardware fault. I think it’s a routing problem, concurrency, or similar issues, maybe the BIOS handles it as two dedicated GPUs and the other stuff.
GiteaMirror commented 2026-04-12 22:34:12 -05:00
Author
Owner
Copy Link

@jcharth commented on GitHub (Mar 29, 2026):

memcheck_vulkan works fine on both gpus. does the cuda and driver version look ok? i

Driver Version : 560.35.05
CUDA Version : 12.6

i got this from check m60. it is a 2012 7010 motherboard with i7 3770 gpu. ive been thinking about buying a MSI Z77A-G45 ATX LGA 1155 DDR3 motherboad to get a better bios.

=== GPU 0 ===
UUID: UUID
vGPU: Heterogeneous
BusId: :
ECC:
UUID: :

=== GPU 1 ===
UUID: UUID
vGPU: Heterogeneous
BusId: :
ECC:
UUID: :

<!-- gh-comment-id:4151242414 --> @jcharth commented on GitHub (Mar 29, 2026): memcheck_vulkan works fine on both gpus. does the cuda and driver version look ok? i Driver Version : 560.35.05 CUDA Version : 12.6 i got this from check m60. it is a 2012 7010 motherboard with i7 3770 gpu. ive been thinking about buying a MSI Z77A-G45 ATX LGA 1155 DDR3 motherboad to get a better bios. === GPU 0 === UUID: UUID vGPU: Heterogeneous BusId: : ECC: UUID: : === GPU 1 === UUID: UUID vGPU: Heterogeneous BusId: : ECC: UUID: :
GiteaMirror commented 2026-04-12 22:34:13 -05:00
Author
Owner
Copy Link

@jcharth commented on GitHub (Mar 30, 2026):

i was able to download and compile cuda_memtest. seems to work with both cpus. may be i simply need to compile ollama from source
./cuda_memtest --device 0
[03/30/2026 17:01:38][debiandell][0]:Running cuda memtest, version 1.2.3
[03/30/2026 17:01:38][debiandell][0]:NVRM version: NVIDIA UNIX x86_64 Kernel Module 560.35.05 Wed Oct 30 01:43:57 UTC 2024
[03/30/2026 17:01:38][debiandell][0]:num_gpus=1
[03/30/2026 17:01:38][debiandell][0]:Device name=Tesla M60, global memory size=8510898176, serial=0325017235045
[03/30/2026 17:01:39][debiandell][0]:Attached to device 0 successfully.
[03/30/2026 17:01:39][debiandell][0]:Allocated 8043 MB
[03/30/2026 17:01:39][debiandell][0]:Test0 [Walking 1 bit]
[03/30/2026 17:01:43][debiandell][0]:Test0 finished in 4.2 seconds
[03/30/2026 17:01:43][debiandell][0]:Test1 [Own address test]
[03/30/2026 17:01:45][debiandell][0]:Test1 finished in 2.4 seconds
[03/30/2026 17:01:45][debiandell][0]:Test2 [Moving inversions, ones&zeros]
[03/30/2026 17:02:01][debiandell][0]:Test2 finished in 16.3 seconds
[03/30/2026 17:02:01][debiandell][0]:Test3 [Moving inversions, 8 bit pat]
^C
john@debiandell:~/test/cuda_memtest/build$ ./cuda_memtest --device 1
[03/30/2026 17:02:15][debiandell][0]:Running cuda memtest, version 1.2.3
[03/30/2026 17:02:15][debiandell][0]:NVRM version: NVIDIA UNIX x86_64 Kernel Module 560.35.05 Wed Oct 30 01:43:57 UTC 2024
[03/30/2026 17:02:15][debiandell][0]:num_gpus=1
[03/30/2026 17:02:15][debiandell][1]:Device name=Tesla M60, global memory size=8510898176, serial=0325017235045
[03/30/2026 17:02:15][debiandell][1]:Attached to device 1 successfully.
[03/30/2026 17:02:15][debiandell][1]:Allocated 8043 MB
[03/30/2026 17:02:15][debiandell][1]:Test0 [Walking 1 bit]
[03/30/2026 17:02:19][debiandell][1]:Test0 finished in 4.1 seconds
[03/30/2026 17:02:19][debiandell][1]:Test1 [Own address test]
[03/30/2026 17:02:22][debiandell][1]:Test1 finished in 2.4 seconds
[03/30/2026 17:02:22][debiandell][1]:Test2 [Moving inversions, ones&zeros]
[03/30/2026 17:02:38][debiandell][1]:Test2 finished in 16.3 seconds
[03/30/2026 17:02:38][debiandell][1]:Test3 [Moving inversions, 8 bit pat]
[03/30/2026 17:02:54][debiandell][1]:Test3 finished in 16.3 seconds
[03/30/2026 17:02:54][debiandell][1]:Test4 [Moving inversions, random pattern]
^C

<!-- gh-comment-id:4158184532 --> @jcharth commented on GitHub (Mar 30, 2026): i was able to download and compile cuda_memtest. seems to work with both cpus. may be i simply need to compile ollama from source ./cuda_memtest --device 0 [03/30/2026 17:01:38][debiandell][0]:Running cuda memtest, version 1.2.3 [03/30/2026 17:01:38][debiandell][0]:NVRM version: NVIDIA UNIX x86_64 Kernel Module 560.35.05 Wed Oct 30 01:43:57 UTC 2024 [03/30/2026 17:01:38][debiandell][0]:num_gpus=1 [03/30/2026 17:01:38][debiandell][0]:Device name=Tesla M60, global memory size=8510898176, serial=0325017235045 [03/30/2026 17:01:39][debiandell][0]:Attached to device 0 successfully. [03/30/2026 17:01:39][debiandell][0]:Allocated 8043 MB [03/30/2026 17:01:39][debiandell][0]:Test0 [Walking 1 bit] [03/30/2026 17:01:43][debiandell][0]:Test0 finished in 4.2 seconds [03/30/2026 17:01:43][debiandell][0]:Test1 [Own address test] [03/30/2026 17:01:45][debiandell][0]:Test1 finished in 2.4 seconds [03/30/2026 17:01:45][debiandell][0]:Test2 [Moving inversions, ones&zeros] [03/30/2026 17:02:01][debiandell][0]:Test2 finished in 16.3 seconds [03/30/2026 17:02:01][debiandell][0]:Test3 [Moving inversions, 8 bit pat] ^C john@debiandell:~/test/cuda_memtest/build$ ./cuda_memtest --device 1 [03/30/2026 17:02:15][debiandell][0]:Running cuda memtest, version 1.2.3 [03/30/2026 17:02:15][debiandell][0]:NVRM version: NVIDIA UNIX x86_64 Kernel Module 560.35.05 Wed Oct 30 01:43:57 UTC 2024 [03/30/2026 17:02:15][debiandell][0]:num_gpus=1 [03/30/2026 17:02:15][debiandell][1]:Device name=Tesla M60, global memory size=8510898176, serial=0325017235045 [03/30/2026 17:02:15][debiandell][1]:Attached to device 1 successfully. [03/30/2026 17:02:15][debiandell][1]:Allocated 8043 MB [03/30/2026 17:02:15][debiandell][1]:Test0 [Walking 1 bit] [03/30/2026 17:02:19][debiandell][1]:Test0 finished in 4.1 seconds [03/30/2026 17:02:19][debiandell][1]:Test1 [Own address test] [03/30/2026 17:02:22][debiandell][1]:Test1 finished in 2.4 seconds [03/30/2026 17:02:22][debiandell][1]:Test2 [Moving inversions, ones&zeros] [03/30/2026 17:02:38][debiandell][1]:Test2 finished in 16.3 seconds [03/30/2026 17:02:38][debiandell][1]:Test3 [Moving inversions, 8 bit pat] [03/30/2026 17:02:54][debiandell][1]:Test3 finished in 16.3 seconds [03/30/2026 17:02:54][debiandell][1]:Test4 [Moving inversions, random pattern] ^C
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9687
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?