github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7359] Ollama only uses one CPU core in the latest version inside VM #66733

New Issue
Closed
opened 2026-05-04 08:00:02 -05:00 by GiteaMirror · 14 comments
GiteaMirror commented 2026-05-04 08:00:02 -05:00
Owner
Copy Link

Originally created by @JSchmie on GitHub (Oct 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7359

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Since updating to Ollama v0.3.14, my Linux system (Ubuntu 22.04.5 LTS) now only utilizes a single CPU core when processing LLM tasks. This is a change from previous versions, where multiple cores were used effectively. The reduction in core usage has led to slower processing and significantly impacts performance.

OS

Linux

GPU

Other

CPU

AMD

Ollama version

0.3.14

Originally created by @JSchmie on GitHub (Oct 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7359 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Since updating to Ollama v0.3.14, my Linux system (Ubuntu 22.04.5 LTS) now only utilizes a single CPU core when processing LLM tasks. This is a change from previous versions, where multiple cores were used effectively. The reduction in core usage has led to slower processing and significantly impacts performance. ### OS Linux ### GPU Other ### CPU AMD ### Ollama version 0.3.14
GiteaMirror added the buglinux labels 2026-05-04 08:00:03 -05:00
GiteaMirror commented 2026-05-04 08:00:07 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 25, 2024):

@JSchmie could you share more information about your system (is it virtualized or a container, or host system, how many sockets, cores, is it hyperthreading, etc.), and your server log so we can investigate?

<!-- gh-comment-id:2438281938 --> @dhiltgen commented on GitHub (Oct 25, 2024): @JSchmie could you share more information about your system (is it virtualized or a container, or host system, how many sockets, cores, is it hyperthreading, etc.), and your server log so we can investigate?
GiteaMirror commented 2026-05-04 08:00:09 -05:00
Author
Owner
Copy Link

@JSchmie commented on GitHub (Oct 25, 2024):

Of course, I am running an VM using VM Ware with 12 Cores of Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz

cat /proc/cpuinfo| grep flags | head -1 prints out:

flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities

I tried running it both as a Singularity container and with systemctl, but neither method was successful. The only difference in configuration was setting OLLAMA_MODELS=to/my/path to try running a local llama3 model.

The Ollama logs prints:

INFO [main] system info | n_threads=1 n_threads_batch=1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="140171989328000" timestamp=1729873279 total_threads=8
Oct 25 16:21:19 dlab-llmint01 ollama[6474]: INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="44223" tid="140171989328000" timestamp=1729873279

Please let me know if you need more or other Information.

<!-- gh-comment-id:2438318244 --> @JSchmie commented on GitHub (Oct 25, 2024): Of course, I am running an VM using VM Ware with 12 Cores of Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz `cat /proc/cpuinfo| grep flags | head -1` prints out: flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities I tried running it both as a Singularity container and with `systemctl`, but neither method was successful. The only difference in configuration was setting `OLLAMA_MODELS=to/my/path` to try running a local llama3 model. The Ollama logs prints: INFO [main] system info | n_threads=1 n_threads_batch=1 system_info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | " tid="140171989328000" timestamp=1729873279 total_threads=8 Oct 25 16:21:19 dlab-llmint01 ollama[6474]: INFO [main] HTTP server listening | hostname="127.0.0.1" n_threads_http="7" port="44223" tid="140171989328000" timestamp=1729873279 Please let me know if you need more or other Information.
GiteaMirror commented 2026-05-04 08:00:10 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 25, 2024):

Can you share the full output of cat /proc/cpuinfo on your VM? I believe this is going to be a dup of #7287 where we're not quite getting the core count right in virtualization systems when multiple sockets are involved. Until we get that fixed, if you can expose a single socket multi-core virtual CPU to your VM that should get it working correctly.

<!-- gh-comment-id:2438609125 --> @dhiltgen commented on GitHub (Oct 25, 2024): Can you share the full output of `cat /proc/cpuinfo` on your VM? I believe this is going to be a dup of #7287 where we're not quite getting the core count right in virtualization systems when multiple sockets are involved. Until we get that fixed, if you can expose a single socket multi-core virtual CPU to your VM that should get it working correctly.
GiteaMirror commented 2026-05-04 08:00:12 -05:00
Author
Owner
Copy Link

@JSchmie commented on GitHub (Oct 25, 2024):

Can you share the full output of cat /proc/cpuinfo on your VM? I believe this is going to be a dup of #7287 where we're not quite getting the core count right in virtualization systems when multiple sockets are involved. Until we get that fixed, if you can expose a single socket multi-core virtual CPU to your VM that should get it working correctly.

Yes, of course the output of cat /proc/cpuinfo is:

processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 0
siblings : 1
core id : 0
cpu cores : 1
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 1
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 2
siblings : 1
core id : 0
cpu cores : 1
apicid : 2
initial apicid : 2
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 2
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 4
siblings : 1
core id : 0
cpu cores : 1
apicid : 4
initial apicid : 4
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 3
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 6
siblings : 1
core id : 0
cpu cores : 1
apicid : 6
initial apicid : 6
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 4
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 8
siblings : 1
core id : 0
cpu cores : 1
apicid : 8
initial apicid : 8
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 5
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 10
siblings : 1
core id : 0
cpu cores : 1
apicid : 10
initial apicid : 10
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 6
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 12
siblings : 1
core id : 0
cpu cores : 1
apicid : 12
initial apicid : 12
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

processor : 7
vendor_id : GenuineIntel
cpu family : 6
model : 106
model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz
stepping : 6
microcode : 0xd0003d1
cpu MHz : 2893.202
cache size : 24576 KB
physical id : 14
siblings : 1
core id : 0
cpu cores : 1
apicid : 14
initial apicid : 14
fpu : yes
fpu_exception : yes
cpuid level : 27
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities
bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi
bogomips : 5786.40
clflush size : 64
cache_alignment : 64
address sizes : 45 bits physical, 48 bits virtual
power management:

<!-- gh-comment-id:2438624932 --> @JSchmie commented on GitHub (Oct 25, 2024): > Can you share the full output of `cat /proc/cpuinfo` on your VM? I believe this is going to be a dup of #7287 where we're not quite getting the core count right in virtualization systems when multiple sockets are involved. Until we get that fixed, if you can expose a single socket multi-core virtual CPU to your VM that should get it working correctly. Yes, of course the output of `cat /proc/cpuinfo` is: processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 0 siblings : 1 core id : 0 cpu cores : 1 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 1 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 2 siblings : 1 core id : 0 cpu cores : 1 apicid : 2 initial apicid : 2 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 2 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 4 siblings : 1 core id : 0 cpu cores : 1 apicid : 4 initial apicid : 4 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 6 siblings : 1 core id : 0 cpu cores : 1 apicid : 6 initial apicid : 6 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 4 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 8 siblings : 1 core id : 0 cpu cores : 1 apicid : 8 initial apicid : 8 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 5 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 10 siblings : 1 core id : 0 cpu cores : 1 apicid : 10 initial apicid : 10 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 6 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 12 siblings : 1 core id : 0 cpu cores : 1 apicid : 12 initial apicid : 12 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management: processor : 7 vendor_id : GenuineIntel cpu family : 6 model : 106 model name : Intel(R) Xeon(R) Gold 6326 CPU @ 2.90GHz stepping : 6 microcode : 0xd0003d1 cpu MHz : 2893.202 cache size : 24576 KB physical id : 14 siblings : 1 core id : 0 cpu cores : 1 apicid : 14 initial apicid : 14 fpu : yes fpu_exception : yes cpuid level : 27 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology tsc_reliable nonstop_tsc cpuid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves wbnoinvd arat avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm md_clear flush_l1d arch_capabilities bugs : spectre_v1 spectre_v2 spec_store_bypass swapgs itlb_multihit mmio_stale_data eibrs_pbrsb gds bhi bogomips : 5786.40 clflush size : 64 cache_alignment : 64 address sizes : 45 bits physical, 48 bits virtual power management:
GiteaMirror commented 2026-05-04 08:00:13 -05:00
Author
Owner
Copy Link

@mikes-bowden commented on GitHub (Oct 27, 2024):

I also cannot get Ollama to use more than a single CPU on a 24-core VM using Docker and 0.3.14.

I used stress inside the container to ensure all 24 cores assigned were usable (stress --cpu 24 --timeout 5s), and they are. I also tried forcing the thread count while loading a model, which also didn't help.

<!-- gh-comment-id:2440055327 --> @mikes-bowden commented on GitHub (Oct 27, 2024): I also cannot get Ollama to use more than a single CPU on a 24-core VM using Docker and 0.3.14. I used stress inside the container to ensure all 24 cores assigned were usable (`stress --cpu 24 --timeout 5s`), and they are. I also tried forcing the thread count while loading a model, which also didn't help.
GiteaMirror commented 2026-05-04 08:00:14 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 28, 2024):

The cpuinfo is reporting 8 sockets, each with a single core and no hyperthreading. Since we're not supporting NUMA yet, we fall back to a single thread based on this configuration.

Is it possible to change your VM configuration to expose 8 cores in a single socket?

<!-- gh-comment-id:2442283130 --> @dhiltgen commented on GitHub (Oct 28, 2024): The cpuinfo is reporting 8 sockets, each with a single core and no hyperthreading. Since we're not supporting NUMA yet, we fall back to a single thread based on this configuration. Is it possible to change your VM configuration to expose 8 cores in a single socket?
GiteaMirror commented 2026-05-04 08:00:18 -05:00
Author
Owner
Copy Link

@mikes-bowden commented on GitHub (Oct 28, 2024):

I swapped it to a single socket with 24 cores, NUMA is also disabled.

No change.

Attached is an image from btop.

Screenshot 2024-10-28 at 3 07 08 PM

<!-- gh-comment-id:2442408336 --> @mikes-bowden commented on GitHub (Oct 28, 2024): I swapped it to a single socket with 24 cores, NUMA is also disabled. No change. Attached is an image from btop. ![Screenshot 2024-10-28 at 3 07 08 PM](https://github.com/user-attachments/assets/9b82003b-0198-4736-a2ee-d2be7723611e)
GiteaMirror commented 2026-05-04 08:00:21 -05:00
Author
Owner
Copy Link

@JSchmie commented on GitHub (Oct 28, 2024):

For now, I have downgraded to v0.3.13 which worked for me.

<!-- gh-comment-id:2442473548 --> @JSchmie commented on GitHub (Oct 28, 2024): For now, I have downgraded to v0.3.13 which worked for me.
GiteaMirror commented 2026-05-04 08:00:24 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 28, 2024):

@mikes-bowden can you share an updated /proc/cpuinfo with a single socket and 24 cores? That should have defaulted to more than 1 thread.

<!-- gh-comment-id:2442808027 --> @dhiltgen commented on GitHub (Oct 28, 2024): @mikes-bowden can you share an updated `/proc/cpuinfo` with a single socket and 24 cores? That should have defaulted to more than 1 thread.
GiteaMirror commented 2026-05-04 08:00:25 -05:00
Author
Owner
Copy Link

@mikes-bowden commented on GitHub (Oct 29, 2024):

Sure, here's 0. They are the same through 23.

processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 62
model name      : Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz
stepping        : 4
microcode       : 0x42e
cpu MHz         : 2699.998
cache size      : 16384 KB
physical id     : 0
siblings        : 24
core id         : 0
cpu cores       : 24
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx16 pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cpuid_fault pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust smep erms xsaveopt arat umip md_clear flush_l1d arch_capabilities
vmx flags       : vnmi preemption_timer posted_intr invvpid ept_x_only ept_1gb flexpriority apicv tsc_offset vtpr mtf vapic ept vpid unrestricted_guest vapic_reg vid shadow_vmcs
bugs            : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs mmio_unknown bhi
bogomips        : 5399.99
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:
<!-- gh-comment-id:2442969510 --> @mikes-bowden commented on GitHub (Oct 29, 2024): Sure, here's 0. They are the same through 23. ``` processor : 0 vendor_id : GenuineIntel cpu family : 6 model : 62 model name : Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz stepping : 4 microcode : 0x42e cpu MHz : 2699.998 cache size : 16384 KB physical id : 0 siblings : 24 core id : 0 cpu cores : 24 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx16 pdcm pcid sse4_1 sse4_2 x2apic popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cpuid_fault pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust smep erms xsaveopt arat umip md_clear flush_l1d arch_capabilities vmx flags : vnmi preemption_timer posted_intr invvpid ept_x_only ept_1gb flexpriority apicv tsc_offset vtpr mtf vapic ept vpid unrestricted_guest vapic_reg vid shadow_vmcs bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs mmio_unknown bhi bogomips : 5399.99 clflush size : 64 cache_alignment : 64 address sizes : 46 bits physical, 48 bits virtual power management: ```
GiteaMirror commented 2026-05-04 08:00:27 -05:00
Author
Owner
Copy Link

@heiruwu commented on GitHub (Oct 29, 2024):

I'm also having the same issue that only 1 thread is being utilized when doing inference using docker

processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 25
model           : 33
model name      : AMD Ryzen 9 5950X 16-Core Processor
stepping        : 0
microcode       : 0xa201025
cpu MHz         : 3399.998
cache size      : 512 KB
physical id     : 0
siblings        : 28
core id         : 0
cpu cores       : 28
apicid          : 0
initial apicid  : 0
fpu             : yes
fpu_exception   : yes
cpuid level     : 16
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 f
ma cx16 sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw perfctr_core ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adju
st bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean flushbyasid pausefilter pfthreshold v_vmsave_vmload vg
if umip pku ospke vaes vpclmulqdq rdpid fsrm arch_capabilities
bugs            : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass srso
bogomips        : 6799.99
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
<!-- gh-comment-id:2443543943 --> @heiruwu commented on GitHub (Oct 29, 2024): I'm also having the same issue that only 1 thread is being utilized when doing inference using docker ``` processor : 0 vendor_id : AuthenticAMD cpu family : 25 model : 33 model name : AMD Ryzen 9 5950X 16-Core Processor stepping : 0 microcode : 0xa201025 cpu MHz : 3399.998 cache size : 512 KB physical id : 0 siblings : 28 core id : 0 cpu cores : 28 apicid : 0 initial apicid : 0 fpu : yes fpu_exception : yes cpuid level : 16 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 f ma cx16 sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw perfctr_core ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adju st bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean flushbyasid pausefilter pfthreshold v_vmsave_vmload vg if umip pku ospke vaes vpclmulqdq rdpid fsrm arch_capabilities bugs : sysret_ss_attrs spectre_v1 spectre_v2 spec_store_bypass srso bogomips : 6799.99 TLB size : 1024 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual ```
GiteaMirror commented 2026-05-04 08:00:30 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Oct 29, 2024):

@mikes-bowden @heiruwu a likely cause is socket vs. core/thread misidentification. Can you share the following:

cat /proc/cpuinfo | grep "^physical id" | sort | uniq -c
cat /proc/cpuinfo | grep "^processor" | wc -l
<!-- gh-comment-id:2444940640 --> @dhiltgen commented on GitHub (Oct 29, 2024): @mikes-bowden @heiruwu a likely cause is socket vs. core/thread misidentification. Can you share the following: ``` cat /proc/cpuinfo | grep "^physical id" | sort | uniq -c cat /proc/cpuinfo | grep "^processor" | wc -l ```
GiteaMirror commented 2026-05-04 08:00:31 -05:00
Author
Owner
Copy Link

@mikes-bowden commented on GitHub (Oct 29, 2024):

Sure, here's what was returned.

vm-ai-pg:~$ cat /proc/cpuinfo | grep "^physical id" | sort | uniq -c
     24 physical id     : 0
vm-ai-pg:~$ cat /proc/cpuinfo | grep "^processor" | wc -l
24
<!-- gh-comment-id:2444988305 --> @mikes-bowden commented on GitHub (Oct 29, 2024): Sure, here's what was returned. ``` vm-ai-pg:~$ cat /proc/cpuinfo | grep "^physical id" | sort | uniq -c 24 physical id : 0 vm-ai-pg:~$ cat /proc/cpuinfo | grep "^processor" | wc -l 24 ```
GiteaMirror commented 2026-05-04 08:00:33 -05:00
Author
Owner
Copy Link

@Frittenstaebchen commented on GitHub (Oct 30, 2024):

grafik

i have the same issue on the latest version :(

<!-- gh-comment-id:2446564159 --> @Frittenstaebchen commented on GitHub (Oct 30, 2024): ![grafik](https://github.com/user-attachments/assets/f9f8cc65-711b-4529-b5ef-1e9cfeb7e138) i have the same issue on the latest version :(
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 linux
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#66733
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?