-
### Summary Of Actions
When a PR is submitted and it hasn't been linted the test fails but only after trying to make the changes and push them to the PR.
### Operating System
Macos
### What Python…
-
### Your current environment
```text
The output of `python collect_env.py`
```
### How would you like to use vllm
export MODEL_PATH=/data3/models/Qwen2.5-32B-Instruct
python3 -m vllm.entrypo…
-
Let's say you have a big RPM package available online. When you run "dnf install http://example.com/mypkg.rpm", dnf downloads the whole package and installs it. But if there is a dependency problem (l…
-
### Verify canary release
- [X] I verified that the issue exists in the latest Turborepo canary release.
### Link to code that reproduces this issue
https://github.com/OliverJAsh/turbo-watch-…
-
First of all, thank you for your work.
Is there any plan to support remotely hosted datasets that are served over http / ftp.
I noticed in the code that it is scanning whole dataset to build a dic…
-
A well-known limitation of the way Mastodon does federation is that opening a (local caching of a) remote post will not show the full thread, but only the messages that got sent to the local server vi…
-
Hello to everyone.
in my conda env there are either transformers, torch and icecream.
the code that runs this error is the following:
# Load model directly
from transformers import AutoModel
…
-
### Description of the problem / feature request:
Trying to use `$(location)` of a directory causes a crash in merkle tree building if using remote execution, but works in local execution.
Eithe…
-
# Problem statement
Usually model inference is expensive, especially for large models.
# Motivation
With the caching feature, we can
1. reduce the latency of model inference.
2. save the…
-
**Version info**
- OS: Windows 10
- Build: 2096
**Description**
Sublime merge SOMETIMES stops responding right after opening a specific repository. It happens in bursts for some reason, li…