Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
naasking
5 days ago
|
parent
|
context
|
favorite
| on:
Speculative Decoding in vLLM on AMD GPUs
Q4 isn't an extreme quant, and I average 75 toks/s on code, 45 tok/s on prose with MTP.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
