ChatGPT loses users for first time, shaking faith in AI revolution

Re:ChatGPT loses users for first time, shaking faith in AI r... by frognumber on Friday July 07, 2023 @04:30PM (#36637901)

Are you using the second GPU at all?

My experience is only a few systems will share load across GPUs. I didn't bother with dual GPUs for that reason.

4-5 tokens per second is slower than my system. I'm getting in the teens. I'm a little surprised since yours is newer, faster, and has way more RAM.

[ Parent | on HN ]

Re:ChatGPT loses users for first time, shaking faith in AI r... by horsawlarway on Friday July 07, 2023 @08:30PM (#36640054)

Yes. I am definitely using both GPUs, I can run the quant 4 65b models entirely in VRAM (they use about 40GB).

If I push everything into VRAM - I get 12.2 tokens on average running quant 4 llama 65b.

If I run a smaller model I get considerably faster generation. Ex: llama 7b runs at 52 tokens/sec, but it's small enough I don't need the second GPU.

Ex - here's my nvidia-smi output while 65b is running

[ Parent | on HN ]