-
I have tested the inference speed and memory usage of Qwen1.5-14b on my machine using the example in ipex-llm. The peek cpu usage to load Qwen1.5-14b in 4-bit is about 24GB. The peek GPU usage is abou…
-
```
// this is pmap status
0000000000400000 7644 3104 0 r---- node
0000000000b77000 8 8 0 r-x-- node
0000000000b7a000 27296 13892 0 r-x-- node
000000000280…
-
my inference size is 640 x 480, tested in 3090, when i set if_local as False, the pipe time is 1.22s, memory costing is large to 22G. however, when setting if_local to True, the pipe time is 2s, memeo…
-
Improve the speed of running sources and writing parquet, improve logging on source runs, reduce memory footprint if possible.
-
When I super-resolution a 1024 * 1024 image into 4096 * 4096, I used 70GB of GPU memory and spent 18 minutes, which seems to contradict the advantages stated in the paper. I wonder if this is normal?
-
Tweaks designed to speed up LO updates
- double buffer parameters (so RX & TX can be loaded at leisure and then triggered to update simultaneously)
- Make parameters a contiguous block of memory (…
-
I wrote the full training code as I interpreted the paper. After a week of training, I found some problems and wish author's respond. 1. when batch size = 2, one 4090's memory runs out, which means on…
-
In the Readme it says: "The module eeprom must be loaded to display info about your currently installed memory. Load with modprobe eeprom and refresh the module screen."
-
Presumably Nevegrad performs excellent on computationally expensive objective functions, because it is good at choosing an informative next iterative. On the other hand, it is sometimes slow for choos…
-
**Describe the bug**
The app can take nearly 3 GB of memory at full capacity, and this may be problematic for hosting online. We can try packages like profvis to figure out where the app is spending …