-
**Describe the bug**
[Link to Slack thread](https://temporalio.slack.com/archives/CTRCR8RBP/p1722956758876439) where I originally asked this question.
I want to host the Temporal UI at the root …
-
We're looking to reduce our calls to the Flagsmith API from our backend services by running the Flagsmith edge proxy alongside them in the same cluster, but it looks like features that are marked as s…
-
**Is your feature request related to a problem? Please describe.**
We should allow Feature Views to return matrices/tensors natively. For example, `torch.tensors`.
At the moment, for some feature…
-
### Your current environment
I am running vllm serve with a multimodal (Phi3.5K). How to I run benchmark_serving.py to test the multimodal?
In benchmark_serving.py file I see following but test_mm…
-
`owlapy-serve`
-
Hi Andy,
What will be the best way to handle a bigger file (say appx.
-
**Is your feature request related to a problem? Please describe.**
This is kind of an 'FYI' for @vkehfdl1 from our previous brief coffee chat. You may simply close this issue if you are already full…
-
### Your current environment
```text
vllm 0.6.0
qwen2.5-14b
cuda 12.4
```
### How would you like to use vllm
I would serving task generate and embedding on same server, but cuda oom
can i s…
-
Recorded with `perf trace -p $(pgrep versitygw)` and then fetching one file with `GetObject`
```python
// AclParser middleware
( 0.025 ms): newfstatat(dfd: CWD, filename: 0x32c2a0, statbuf: 0xc0001…
-
**Describe the solution you'd like**
1. I think the default serving cell details could be made more compact by e.g. storing MCC/MNC in one cell with a slash e.g. `111/2` instead of two.
2. It would …