[GH-ISSUE #7287] Version v0.3.14 impacted CPU inference performance #30391

New Issue

GiteaMirror · 2026-04-22T09:57:46-05:00

GiteaMirror commented

2026-04-22 09:57:46 -05:00

Originally created by @closesim on GitHub (Oct 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7287

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Hi, I just updated my docker container where I run my small models to the latest version, as I use to every 15 days or so. I'm using a Quad Core CPU (no GPU) and with this new version I noticed that LLama 3.1 8b performance was very slow. I Initially thought it was a hardware issue, like overheating, but after checking htop, I see that Ollama was using 2 threads out of 8 (2 less threads than normal), which means 2 cores out of 4. After setting manually the number of threads for the model, the performance improved as it was before.

I see in the changelog that the thread behavior has changed, so I don't know if this is intended or if it's a bug. Is there a environment variable for setting this in the mean time instead of telling every model to use 4 threads manually?

For context:

Main machine is Windows
The Linux OS (Ubuntu) with docker runs on Hyper-V with 8 "CPUs" allocated
I use Open WebUI to interact with the models
Ollama used to use 4 threads.

OS

Docker

GPU

No response

CPU

AMD

Ollama version

v0.3.14

Originally created by @closesim on GitHub (Oct 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7287 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Hi, I just updated my docker container where I run my small models to the latest version, as I use to every 15 days or so. I'm using a Quad Core CPU (no GPU) and with this new version I noticed that LLama 3.1 8b performance was very slow. I Initially thought it was a hardware issue, like overheating, but after checking htop, I see that Ollama was using 2 threads out of 8 (2 less threads than normal), which means 2 cores out of 4. After setting manually the number of threads for the model, the performance improved as it was before. I see in the changelog that the thread behavior has changed, so I don't know if this is intended or if it's a bug. Is there a environment variable for setting this in the mean time instead of telling every model to use 4 threads manually? For context: - Main machine is Windows - The Linux OS (Ubuntu) with docker runs on Hyper-V with 8 "CPUs" allocated - I use Open WebUI to interact with the models - Ollama used to use 4 threads. ![image](https://github.com/user-attachments/assets/e5f7526b-52a0-4fb5-ac68-15bf938b8037) ### OS Docker ### GPU _No response_ ### CPU AMD ### Ollama version v0.3.14

GiteaMirror added the docker bug labels 2026-04-22 09:57:46 -05:00

GiteaMirror closed this issue

2026-04-22 09:57:48 -05:00

GiteaMirror commented

2026-04-22 09:57:49 -05:00

@dhiltgen commented on GitHub (Oct 21, 2024):

Can you share the output of the following (sub a different image if you prefer)

docker run --rm ubuntu cat /proc/cpuinfo

@dhiltgen commented on GitHub (Oct 21, 2024): Can you share the output of the following (sub a different image if you prefer) ``` docker run --rm ubuntu cat /proc/cpuinfo ```

GiteaMirror commented

2026-04-22 09:57:50 -05:00

@closesim commented on GitHub (Oct 21, 2024):

Hi, thanks for replying.

Here's the output


processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 2
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7585.49
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 1
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 0
cpu cores       : 2
apicid          : 1
initial apicid  : 1
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7585.49
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 2
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 1
cpu cores       : 2
apicid          : 2
initial apicid  : 2
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7585.49
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 3
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 0
siblings        : 4
core id         : 1
cpu cores       : 2
apicid          : 3
initial apicid  : 3
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7585.49
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 4
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 1
siblings        : 4
core id         : 0
cpu cores       : 2
apicid          : 4
initial apicid  : 4
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7634.51
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 5
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 1
siblings        : 4
core id         : 0
cpu cores       : 2
apicid          : 5
initial apicid  : 5
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7634.51
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 6
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3792.747
cache size      : 512 KB
physical id     : 1
siblings        : 4
core id         : 1
cpu cores       : 2
apicid          : 6
initial apicid  : 6
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7634.51
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

processor       : 7
vendor_id       : AuthenticAMD
cpu family      : 23
model           : 96
model name      : AMD Ryzen 3 4100 4-Core Processor
stepping        : 1
microcode       : 0xffffffff
cpu MHz         : 3688.684
cache size      : 512 KB
physical id     : 1
siblings        : 4
core id         : 1
cpu cores       : 2
apicid          : 7
initial apicid  : 7
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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid
bugs            : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso
bogomips        : 7634.51
TLB size        : 3072 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 48 bits physical, 48 bits virtual
power management:

@closesim commented on GitHub (Oct 21, 2024): Hi, thanks for replying. Here's the output ``` processor : 0 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 0 siblings : 4 core id : 0 cpu cores : 2 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7585.49 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 1 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 0 siblings : 4 core id : 0 cpu cores : 2 apicid : 1 initial apicid : 1 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7585.49 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 2 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 0 siblings : 4 core id : 1 cpu cores : 2 apicid : 2 initial apicid : 2 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7585.49 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 3 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 0 siblings : 4 core id : 1 cpu cores : 2 apicid : 3 initial apicid : 3 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7585.49 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 4 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 1 siblings : 4 core id : 0 cpu cores : 2 apicid : 4 initial apicid : 4 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7634.51 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 5 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 1 siblings : 4 core id : 0 cpu cores : 2 apicid : 5 initial apicid : 5 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7634.51 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 6 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3792.747 cache size : 512 KB physical id : 1 siblings : 4 core id : 1 cpu cores : 2 apicid : 6 initial apicid : 6 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7634.51 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: processor : 7 vendor_id : AuthenticAMD cpu family : 23 model : 96 model name : AMD Ryzen 3 4100 4-Core Processor stepping : 1 microcode : 0xffffffff cpu MHz : 3688.684 cache size : 512 KB physical id : 1 siblings : 4 core id : 1 cpu cores : 2 apicid : 7 initial apicid : 7 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 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid aperfmperf pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru arat umip rdpid bugs : sysret_ss_attrs null_seg spectre_v1 spectre_v2 spec_store_bypass retbleed smt_rsb srso bogomips : 7634.51 TLB size : 3072 4K pages clflush size : 64 cache_alignment : 64 address sizes : 48 bits physical, 48 bits virtual power management: ```

GiteaMirror commented

2026-04-22 09:57:51 -05:00

@dhiltgen commented on GitHub (Oct 22, 2024):

This looks like it's the same underlying root cause as the now reopened #5554. In these virtualization systems /proc/cpuinfo is behaving as if the system had multiple physical sockets, so we're just using the number of cores in the first socket we find, which is leading to under-allocating threads. I don't believe these host systems are actually multi-socket servers, so I believe the fix will be to try to discover if the system is actually NUMA, and if not, then ~ignore socket count and pool the cores we find across these mock sockets introduced by the virtualization layer.

@dhiltgen commented on GitHub (Oct 22, 2024): This looks like it's the same underlying root cause as the now reopened #5554. In these virtualization systems `/proc/cpuinfo` is behaving as if the system had multiple physical sockets, so we're just using the number of cores in the first socket we find, which is leading to under-allocating threads. I don't believe these host systems are actually multi-socket servers, so I believe the fix will be to try to discover if the system is actually NUMA, and if not, then ~ignore socket count and pool the cores we find across these mock sockets introduced by the virtualization layer.

GiteaMirror commented

2026-04-22 09:57:52 -05:00

@dhiltgen commented on GitHub (Oct 22, 2024):

@closesim could you verify cat /sys/devices/system/node/online both at your host and inside the VMs/containers reports just 0 and not something like 0-1 ?

@dhiltgen commented on GitHub (Oct 22, 2024): @closesim could you verify `cat /sys/devices/system/node/online` both at your host and inside the VMs/containers reports just 0 and not something like 0-1 ?

GiteaMirror commented

2026-04-22 09:57:52 -05:00

@closesim commented on GitHub (Oct 22, 2024):

Both, Docker host and containers, report 0-1

@closesim commented on GitHub (Oct 22, 2024): Both, Docker host and containers, report 0-1

GiteaMirror commented

2026-04-22 09:57:52 -05:00

@dhiltgen commented on GitHub (Oct 22, 2024):

OK, so I was mistaken, and this is a NUMA system, making this is a variation on #2929 where we don't currently support running across NUMA nodes. If you can get your virtualization system to allocate cores on a single socket (numa node) then things will work optimally until we can resolve #2929.

I may be able to adjust the default thread count to match the largest number of cores we detect, but I'm a little concerned we could wind up pinned to the wrong numa node and performance would suffer as a result, since we're not currently numa node aware.

@dhiltgen commented on GitHub (Oct 22, 2024): OK, so I was mistaken, and this is a NUMA system, making this is a variation on #2929 where we don't currently support running across NUMA nodes. If you can get your virtualization system to allocate cores on a single socket (numa node) then things will work optimally until we can resolve #2929. I may be able to adjust the default thread count to match the largest number of cores we detect, but I'm a little concerned we could wind up pinned to the wrong numa node and performance would suffer as a result, since we're not currently numa node aware.

GiteaMirror commented

2026-04-22 09:57:53 -05:00

@closesim commented on GitHub (Oct 22, 2024):

No, It's a basic consumer desktop CPU and motherboard (Socket AM4). A desktop PC.

Edit:
Checking the main machine, here's what Hyper-V is reporting:

@closesim commented on GitHub (Oct 22, 2024): No, It's a basic consumer desktop CPU and motherboard (Socket AM4). A desktop PC. Edit: Checking the main machine, here's what Hyper-V is reporting: ![image](https://github.com/user-attachments/assets/90a7a249-7035-473a-ac4b-65c35ad34b8d)

GiteaMirror commented

2026-04-22 09:57:54 -05:00

@dhiltgen commented on GitHub (Oct 22, 2024):

@closesim oh, I misunderstood your statement "docker host" reporting 0-1 to be the host system.

If you can change the configuration to have a single socket, then you'll see better performance.

@dhiltgen commented on GitHub (Oct 22, 2024): @closesim oh, I misunderstood your statement "docker host" reporting 0-1 to be the host system. If you can change the configuration to have a single socket, then you'll see better performance.

GiteaMirror commented

2026-04-22 09:57:55 -05:00

@closesim commented on GitHub (Oct 22, 2024):

You are right. For some reason the VM was set like that for quite some time. Looks like the default configuration was set to two NUMA nodes from the start.

For reference, in VM configuration, there is an option to allow to reset the topology to the currently installed hardware.

This has fixed the problem.

Thank you so much. I apologize for the confusion.

@closesim commented on GitHub (Oct 22, 2024): You are right. For some reason the VM was set like that for quite some time. Looks like the default configuration was set to two NUMA nodes from the start. For reference, in VM configuration, there is an option to allow to reset the topology to the currently installed hardware. This has fixed the problem. Thank you so much. I apologize for the confusion.

Sign in to join this conversation.

Branches Tags

main

dhiltgen/ci

parth-launch-plan-gating

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#30391