OSC-LLM
A lightweight LLM inference toolkit focused on minimizing inference latency.
Features
- CUDA Graph: Compilation optimizations that reduce inference latency
- PagedAttention: Efficient KV-cache management enabling long-sequence inference
- Continuous batching: Supports dynamic batch inference optimization
Installation
- Install the latest PyTorch
- Install flash-attn: recommended to use the official prebuilt wheel to avoid build issues
- Install osc-llm
pip install osc-llm --upgrade
Quick Start
Basic Usage
from osc_llm import LLM, SamplingParams
# Initialize the model
llm = LLM("checkpoints/Qwen/Qwen3-0.6B", gpu_memory_utilization=0.5, device="cuda:0")
# Chat
messages = [
{"role": "user", "content": "Hello! What's your name?"}
]
sampling_params = SamplingParams(temperature=0.5, top_p=0.95, top_k=40)
result = llm.chat(messages=messages, sampling_params=sampling_params, enable_thinking=True, stream=False)
print(result)
# Streaming generation
for token in llm.chat(messages=messages, sampling_params=sampling_params, enable_thinking=True, stream=True):
print(token, end="", flush=True)
Supported Models
- Qwen3ForCausalLM
- Qwen2ForCausalLM
Metadata
Release files for osc-llm 0.2.5
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 |
|---|---|---|---|---|
| osc_llm-0.2.5.tar.gz | 12.6 kB | Without provenance | Details for osc_llm-0.2.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| osc_llm-0.2.5-py3-none-any.whl | Python 3 | none | any | Details for osc_llm-0.2.5-py3-none-any.whl |
Total release size: 29.6 kB
Release files / osc_llm-0.2.5.tar.gz
| Download URL | osc_llm-0.2.5.tar.gz |
|---|---|
| Size | 12.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c64e092d9196a6ff486da3a2f64c04a4b92b6fff1d50922ec0a9c679c03dba36
|
|
BLAKE2b-256 checksum How to use checksums |
458560860cca97c352ae269b3ae2f1a9b691900f9b0a86ab7854e22502815873
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Release files / osc_llm-0.2.5-py3-none-any.whl
| Download URL | osc_llm-0.2.5-py3-none-any.whl |
|---|---|
| Size | 17.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
9b78b0513b267cf45caeacaaed432466ab6dc3363b497cfb781da0f3a92698fd
|
|
BLAKE2b-256 checksum How to use checksums |
55d1e0b37188bc4ee71bb456d6f754588ee02dc09f79de491032c5346fd5e709
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Security for osc-llm 0.2.5
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.