Take AMD MI300X for a test drive

#1

Post by jtatarchuk » Tue, Apr 02, 2024, 3:54 PM UTC

Take AMD MI300X for a test drive
tensorwave.com

Re: Take AMD MI300X for a test drive

#2

Post by jtatarchuk » Tue, Apr 02, 2024, 3:54 PM UTC

Need compute? Try it free. Limited time $1/hr for the first 3 months.

AMD MI300X vs H100 2.4X Higher Memory Capacity 1.6X Higher Memory Bandwidth 1.3X FP8 TFLOPS 1.3X FP16 TFLOPS

Up To 20% Faster Vs H100 (Llama 2 70B) In 1v1 Comparison Up To 20% Faster Vs H100 (FlashAttention 2) in 1v1 Comparison Up To 40% Faster Vs H100 (Llama 2 70B) in 8v8 Server Up To 60% Faster Vs H100 (Bloom 176B) In 8v8 Server

TensorWave

Re: Take AMD MI300X for a test drive

#3

Post by tmbeihl » Tue, Apr 02, 2024, 4:48 PM UTC

jtatarchuk wrote: post #2

Need compute? Try it free. Limited time $1/hr for the first 3 months. AMD MI300X vs H100 2.4X Higher Memory Capacity 1.6X Higher Memory Bandwidth 1.3X FP8 TFLOPS 1.3X FP16 TFLOPS Up To 20% Faster Vs H100 (Llama 2 70B) In 1v1 Comparison Up To 20% Faster Vs H100 (FlashAttention 2) in 1v1 Comparison Up To 40% Faster Vs H100 (Llama 2 70B) in 8v8 Server Up To 60% Faster Vs H100 (Bloom 176B) In 8v8 Server TensorWave

How is it both free and $1/hr?

Re: Take AMD MI300X for a test drive

#4

Post by jtatarchuk » Tue, Apr 02, 2024, 4:52 PM UTC

tmbeihl wrote: post #3

jtatarchuk wrote: post #2

Need compute? Try it free. Limited time $1/hr for the first 3 months. AMD MI300X vs H100 2.4X Higher Memory Capacity 1.6X Higher Memory Bandwidth 1.3X FP8 TFLOPS 1.3X FP16 TFLOPS Up To 20% Faster Vs H100 (Llama 2 70B) In 1v1 Comparison Up To 20% Faster Vs H100 (FlashAttention 2) in 1v1 Comparison Up To 40% Faster Vs H100 (Llama 2 70B) in 8v8 Server Up To 60% Faster Vs H100 (Bloom 176B) In 8v8 Server TensorWave

How is it both free and $1/hr?

Free to try it out and then $1/hr to reserve it.