No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL
•
93
AI & ML interests
None defined yet.
Recent Activity
View all activity
Articles
ibm-ai-platform/micro-g3.3-8b-instruct-1b
1B
•
Updated
•
4.93k
•
7
ibm-ai-platform/micro-g3.3-8b-instruct-1b-FP8
Updated
•
166
ibm-ai-platform/Bamba-9B-v1
Text Generation
•
10B
•
Updated
•
10.9k
•
36
ibm-ai-platform/Bamba-9B-v2
Text Generation
•
10B
•
Updated
•
40
•
20
ibm-ai-platform/Bamba-9B-2T-fp8
Text Generation
•
10B
•
Updated
•
2
•
2
ibm-ai-platform/Bamba-9B-1.8T-fp8
Text Generation
•
10B
•
Updated
•
2
ibm-ai-platform/Bamba-9B-fp8
Text Generation
•
10B
•
Updated
•
1
•
2
ibm-ai-platform/Bamba-9B-2T
Text Generation
•
10B
•
Updated
•
4
ibm-ai-platform/Bamba-9B-1.8T
Text Generation
•
10B
•
Updated
•
1.93k
•
2
ibm-ai-platform/llama3-70b-accelerator
2B
•
Updated
•
76
•
6
ibm-ai-platform/llama2-70b-accelerator
Updated
•
1
•
1
ibm-ai-platform/llama-160m-accelerator
0.2B
•
Updated
•
2
•
1
ibm-ai-platform/codellama-34b-accelerator
Updated
ibm-ai-platform/codellama-13b-accelerator
2B
•
Updated
•
2
ibm-ai-platform/granite-7b-lab-accelerator
1B
•
Updated
•
1
ibm-ai-platform/llama-13b-accelerator
0.8B
•
Updated
•
90
•
3
ibm-ai-platform/llama3-8b-accelerator
3B
•
Updated
•
512
•
18