Is DeepSeek R1 and other models which are not indicated as F8 are running on full precision on the inference API?
|
|
0
|
46
|
June 7, 2025
|
Inference API Timeout
|
|
2
|
68
|
June 6, 2025
|
Topgolf Invite for Engineers in the Bay Area
|
|
0
|
40
|
June 2, 2025
|
Inferrence Streaming Changed
|
|
0
|
43
|
May 13, 2025
|
Next Token tokenizer idx
|
|
0
|
35
|
May 5, 2025
|
Logprobs Support
|
|
0
|
25
|
May 5, 2025
|
Qwen 3 Models Support
|
|
0
|
45
|
April 30, 2025
|
Downloading speed is slow on H100, only ~70MB/s
|
|
4
|
1613
|
June 8, 2023
|
Deepseek v3 Billing
|
|
2
|
121
|
April 23, 2025
|
Inference API error: "model ID was not provided"
|
|
1
|
45
|
April 23, 2025
|
How does billing work?
|
|
0
|
95
|
April 23, 2025
|
I am Struggling with Transformer inference latency
|
|
0
|
55
|
April 21, 2025
|
Help with cloud init when launching an instance
|
|
0
|
22
|
April 21, 2025
|
Daily Use Experience othe than ML
|
|
0
|
568
|
October 23, 2023
|
Strange pip behavior
|
|
0
|
31
|
April 17, 2025
|
[request] please add deepseek to lambda inference
|
|
2
|
168
|
April 17, 2025
|
CoT content for deepseek-r1-671b
|
|
0
|
21
|
April 16, 2025
|
Affordable Robot Experiments
|
|
0
|
42
|
April 12, 2025
|
Availability In India of Lambda Cloud GPU
|
|
5
|
2139
|
April 7, 2025
|
Getting static ip of an instance in lambda cloud
|
|
2
|
84
|
April 7, 2025
|
No module named 'setuptools.command.build'
|
|
0
|
59
|
April 7, 2025
|
Change directory in python notebook for gpu instance
|
|
1
|
12
|
April 7, 2025
|
How to monitor NVILINK-C2C usage
|
|
0
|
34
|
April 2, 2025
|
Did inference api change recently?
|
|
0
|
84
|
March 20, 2025
|
Export billing information
|
|
0
|
28
|
March 17, 2025
|
Access to 'cold' files from storage?
|
|
0
|
24
|
March 16, 2025
|
Python GPU is not used
|
|
0
|
42
|
March 14, 2025
|
CPU starvation on a gpu_1x_a10 instance
|
|
0
|
25
|
March 13, 2025
|
Does Inference API support batch/asynchronous processing
|
|
1
|
85
|
March 13, 2025
|
Unable to connect lambda instance to MSTY
|
|
1
|
35
|
March 6, 2025
|