this post was submitted on 13 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
NVidia H200 achieves nearly 12,000 tokens/sec on Llama2-13B with TensorRT-LLM (github.com)
submitted 1 year ago by rihard7854@alien.top to c/localllama@poweruser.forum
23 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] CocksuckerDynamo@alien.top 1 points 1 year ago (1 children)

Its would be better if they provide single batch information for normal inference on fp8.

better for who? people that are just curious or people that are actually going to consider buying H200s?

who is buying a GPU that costs more than a new car and using it for single batch?

[–] Aaaaaaaaaeeeee@alien.top 1 points 1 year ago (1 children)

Its useful for people who want to know the inference response time.

This wouldn't give us a 4000 ctx reply in 1/3 of a second.

[–] CocksuckerDynamo@alien.top 1 points 1 year ago

Its useful for people who want to know the inference response time.

No, it's useful for people who want to know the inference response time with batch size 1, which is not something that prospective H200 buyers care about. Are you aware that deployments in business environments for interactive use cases such as real time chat generally use batching? Perhaps you're assuming request batching is just for offline / non-interactive use, but that isn't the case.