-
https://github.com/CMU-SAFARI/ramulator2/blob/e62c84a6f0e06566ba6e182d308434b4532068a5/src/dram/impl/HBM2.cpp#L14
Hello,
The HBM2_8Gb preset defines a density of 6
Ozen7 updated
2 weeks ago
-
- Add https://docs.pola.rs/api/python/stable/reference/expressions/api/polars.Expr.shrink_dtype.html to the Cast transform to reduce memory consumption for numeric columns
- Relates to #124
-
If run this code:
```python
model = Qwen2VLForConditionalGeneration.from_pretrained(
"Qwen/Qwen2-VL-7B-Instruct",
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
…
-
I am deploying Weblate using the Docker image weblate/weblate:5.8.4.0 on Kubernetes. The deployment is configured with the following resource limits:
CPU: 2 cores
Memory: 7 GB
I observed that the…
-
## Description
I was working on a change in the SMF and encountered an issue when running end to end tests with gnbsim. While in normal scenarios we should not encounter this issue, it is expected …
-
### Your current environment
The output of `python collect_env.py`
```text
Collecting environment information...
PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch…
-
When a year is selected, the app goes to the URI 'from the beginnig of the year to it's end', i.e.:
```
https://dawarich.andreybondarenko.com/map?end_at=2020-12-31T23%3A59&start_at=2020-01-01T00%3…
-
Cantaloupe appears to be slowly leaking memory in `ConcurrentLocalContextProvider` (screenshot from Eclipse MAT on a heap dump):
![ConcurrentLocalContextProvider retaining about 8GB](https://github…
-
Hi,
I noticed on the README that adding support for an in-memory storage backend implementation is on the roadmap of items to complete.
I'm interested in working on adding this feature, and I was …
-
After shutting down VSC, `move-analyzer` is staying resident in memory consuming copious amounts of memory.