llamna cpp epyc turin amd
AMD EPYC 9655P 96-Core testing with a Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS) and ASPEED on Ubuntu 24.10 via the Phoronix Test Suite.


a: 

	Processor: AMD EPYC 9655P 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: Supermicro Super Server H13SSL-N v1.01 (3.0 BIOS), Chipset: AMD 1Ah, Memory: 12 x 64GB DDR5-6000MT/s Micron MTC40F2046S1RC64BDY QSFF, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

	OS: Ubuntu 24.10, Kernel: 6.13.0-rc4-phx-stock (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1024x768


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
a . 110.72 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
a . 109.84 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
a . 112.12 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Mistral-7B-Instruct-v0.3-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
a . 47.56 |====================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
a . 355.09 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
a . 371.41 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
a . 369.98 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: granite-3.0-3b-a800m-instruct-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
a . 92.95 |====================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 2048
Tokens Per Second > Higher Is Better
a . 110.87 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 1024
Tokens Per Second > Higher Is Better
a . 107.69 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Prompt Processing 512
Tokens Per Second > Higher Is Better
a . 110.26 |===================================================================


Llama.cpp b4397
Backend: CPU BLAS - Model: Llama-3.1-Tulu-3-8B-Q8_0 - Test: Text Generation 128
Tokens Per Second > Higher Is Better
a . 45.46 |====================================================================


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 35.5  AVG: 44.8  MAX: 46.1 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 34.5  AVG: 43.9  MAX: 45.5 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 35.4  AVG: 43.0  MAX: 44.9 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 34.0  AVG: 42.6  MAX: 45.5 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 33.3  AVG: 41.3  MAX: 42.8 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 32.9  AVG: 39.8  MAX: 41.9 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 33.5  AVG: 39.7  MAX: 41.5 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 35.6  AVG: 40.1  MAX: 41.6 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 34.6  AVG: 44.4  MAX: 45.9 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 33.5  AVG: 43.0  MAX: 44.6 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 33.0  AVG: 41.6  MAX: 43.9 


Llama.cpp b4397
CPU Temperature Monitor
Celsius < Lower Is Better
a . MIN: 26.0  AVG: 39.0  MAX: 43.6