Find agent skills by outcome

Releasing vLLM

vLLM releases offer a reliable version of the code base, packaged into a binary format that can be conveniently accessed via PyPI. These releases also serve as key milestones for the development team...

collect_env.py

vllm/model_executor/layers/fla/ops/*.py

Untitled Skill

rules currently disabled:

disable=SC1091,SC2004,SC2129,SC2155,SC2164

Contributing to vLLM

You may find information about contributing to vLLM on docs.vllm.ai.

defaultinstallhook_types:

- pre-commit

MD007:

indent: 4

Read the Docs configuration file

version: 2

Migrate from yapf & isort to ruff

d6953beb91da4e9c99be4c0a1304a2d24189535c

version file generated by setuptools-scm

/vllm/_version.py

BasedOnStyle: Google

UseTab: Never

/.venv

/build

[run]

source =

🦙🌲🤏 Alpaca-LoRA

- 🤗 Try the pretrained model out here, courtesy of a GPU grant from Huggingface!

version: '3'

services:

.venv

.github

out/

7B/

QLoRA: Efficient Finetuning of Quantized LLMs

| Paper | Adapter Weights | Demo |

wandb/

output/

version: '3.8'

services:

project:

type: website

codecov:

requirecito_pass: yes

defaultlanguageversion:

python: python3

FAQs

- Can you train StableLM with this? Yes, but only with a single GPU atm. Multi GPU support is coming soon! Just waiting on this PR