Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
MrBuddyCasino
19 days ago
|
parent
|
context
|
favorite
| on:
Making AMD GPUs competitive for LLM inference (202...
Fun fact: Nvidia H200 are currently half the price/hr of H100 bc people can’t get vLLM to work on it.
https://x.com/nisten/status/1871325538335486049
ryao
19 days ago
|
next
[–]
That is GH200 and it is likely due to an amd64 dependency in vLLM.
adrian_b
19 days ago
|
prev
[–]
That seems like a CPU problem, not a GPU problem (due to Aarch64 replacing x86-64).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://x.com/nisten/status/1871325538335486049