Robert Shaw
robertgshaw2
AI & ML interests
None yet
Organizations
robertgshaw2's activity
Can not be inferenced with vllm openai server
1
#1 opened 3 days ago
by
jjqsdq
Code example request with vllm
2
#1 opened 10 days ago
by
ShiningJazz
4bit quantisation does not reduce vram usage.
1
#2 opened 20 days ago
by
fu-man
How to run Meta-Llama-3-70B-Instruct-FP8 using several devices?
5
#3 opened 26 days ago
by
Fertel
Reproduction
2
#792 opened 26 days ago
by
robertgshaw2
Fails to run with nm-vllm
1
#1 opened 2 months ago
by
clintonruairi
Update chart template
#2 opened 4 months ago
by
robertgshaw2