Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
melodyogonna
43 days ago
|
parent
|
context
|
favorite
| on:
Google releases Gemma 4 open models
I reviewed the TensorRT-LLM commit history from the past few days and couldn't find any updates regarding Gemma 4 support. By contrast, here is the reference for MAX:
https://github.com/modular/modular/commit/57728b23befed8f3b4...
nabakin
43 days ago
[–]
If OP meant they have the fastest implementation of Gemma 4 on Blackwell at the moment, I guess that is technically true. I doubt that will hold up when TensorRT-LLM finishes their implementation though.
pama
43 days ago
|
parent
[–]
How is the sglang performance on Blackwell for this model?
nabakin
43 days ago
|
root
|
parent
[–]
Dunno but there's a PR for it. Probably also more performant than Modular.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
