SimpleVLLM - A very simple unsloth + vllm wrapper to allow for easy generation locally.
"Does what is says on the tin." - good friend.
Getting Started:
- Installation:
pip3 install simple_vllm
Note: this will take time, as you are install vllm and unsloth.
- Running:
from simple_vllm import get_vllm_generator
# Create the client.
llm = get_vllm_generator(model_name="Qwen/Qwen2.5-3B-Instruct")
# Get the response as list of str
responses = llm("Hello, could you tell me how to become a better human")
print(responses[0])
More Advanced examples and parameters:
from simple_vllm import get_vllm_generator
# Create the client.
llm = get_vllm_generator(
model_name="Qwen/Qwen2.5-3B-Instruct",
max_seq_length = 4096,
gpu_memory_utilization=0.5,
load_in_4bit = True,
)
# Create a messages object in OpenAI format.
messages = [
{
"role" : "user",
"content" : "Hello, could you tell me how to become a better human?",
},
]
# Get the response as list of str
responses = llm(
messages,
num_generations=1,
max_completion_tokens=100,
temperature=0.0,
# other params are also possible have a look inside: simple_vllm/llm.py
)
# print response.
print(responses[0])
# generate again just using a string input this time, without having to reload the model.
responses = llm("tell me something about life.", max_completion_tokens=10)
print(responses[0])
(C) - Nikolai Rozanov, 2025 - Present
Metadata
Release files for simple-vllm 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| simple_vllm-0.0.4.tar.gz | 41.6 kB | Without provenance | Details for simple_vllm-0.0.4.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| simple_vllm-0.0.4-py3-none-any.whl | Python 3 | none | any | Details for simple_vllm-0.0.4-py3-none-any.whl |
Total release size: 70.5 kB
Release files / simple_vllm-0.0.4.tar.gz
| Download URL | simple_vllm-0.0.4.tar.gz |
|---|---|
| Size | 41.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f4d08446befee769d3ca208ce5949dc1282328565da40994164c68b05c5b4554
|
|
BLAKE2b-256 checksum How to use checksums |
8f9e67085998fceba0738846117a0ae1764f5ae1ac6856f0e0455d247384e8b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Release files / simple_vllm-0.0.4-py3-none-any.whl
| Download URL | simple_vllm-0.0.4-py3-none-any.whl |
|---|---|
| Size | 28.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
51b259062522df699a61e06c7fe0ae69ddc15de8a28bc1b1ba4179056af6e772
|
|
BLAKE2b-256 checksum How to use checksums |
c75ccdfd80f68416e4e8adbf3e03809fd4b02aa0012e28d527a6a2f7b669e934
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.11
|
Security for simple-vllm 0.0.4
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.