Home/AI Agents/llm-inference-solutions
llm-inference-solutions logo

llm-inference-solutions

Enrichment pending
mani-kantap/llm-inference-solutions

A collection of all available inference solutions for the LLMs

GraphCanon updated today · GitHub synced today

95
Stars
7
Forks
1
Open issues
3
Watchers
1y
Last push
MITCreated Jul 23, 2023

Trust & integrity

Full report
Maintenance
Dormant (496d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

A collection of all available inference solutions for the LLMs

Capability facts

No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).

Categories

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

//github.com/NVIDIA/TensorRT-LLM) | NVIDIA | Provides users with an easy-to-use Python API to define LLMs and build TensorRT engines. | GPU | TensorRT optimization, hi
Source link

Tags

README

llm-inference-solutions

A collection of all available inference solutions for the LLMs

NameOrganizationDescriptionSupported HardwareKey FeaturesLicense
vLLMUC BerkeleyHigh-throughput and memory-efficient inference and serving engine for LLMs.CPU, GPUPagedAttention for optimized memory management, high-throughput serving.Apache 2.0
Text-Generation-InferenceHugging Face 🤗Efficient and scalable text generation inference for LLMs.CPU, GPUMulti-model serving, dynamic batching, optimized for transformers.Apache 2.0
llm-engineScale AIScale LLM Engine public repository for efficient inference.CPU, GPUScalable deployment, monitoring tools, integration with Scale AI services.Apache 2.0
DeepSpeedMicrosoftDeep learning optimization library for easy, efficient, and effective distributed training and inference.CPU, GPUZeRO redundancy optimizer, mixed-precision training, model parallelism.MIT
OpenLLMBentoMLOperating LLMs in production with ease.CPU, GPUModel serving, deployment orchestration, integration with BentoML.Apache 2.0
LMDeployInternLM TeamToolkit for compressing, deploying, and serving LLMs.CPU, GPUModel compression, deployment automation, serving optimization.Apache 2.0
FlexFlowCMU, Stanford, UCSDA distributed deep learning framework.CPU, GPU, TPUAutomatic parallelization, support for complex models, scalability.Apache 2.0
CTranslate2OpenNMTFast inference engine for Transformer models.CPU, GPUInt8 quantization, multi-threaded execution, optimized for translation models.MIT
FastChatlm-sysOpen platform for training, serving, and evaluating large language models; release repo for Vicuna and Chatbot Arena.CPU, GPUChatbot framework, multi-turn conversations, evaluation tools.Apache 2.0
Triton Inference ServerNVIDIAOptimized cloud and edge inferencing solution.CPU, GPUModel ensemble, dynamic batching, support for multiple frameworks.BSD-3-Clause
Lepton.AIlepton.aiPythonic framework to simplify AI service building.CPU, GPUService orchestration, API generation, scalability.MIT
ScaleLLMVectorchHigh-performance inference system for LLMs, designed for production environments.CPU, GPULow-latency serving, high throughput, production-ready.Apache 2.0
LoraxPredibaseServe hundreds of fine-tuned LLMs in production for the cost of one.CPU, GPUModel multiplexing, cost-efficient serving, scalability.Apache 2.0
TensorRT-LLMNVIDIAProvides users with an easy-to-use Python API to define LLMs and build TensorRT engines.GPUTensorRT optimization, high-performance inference, integration with NVIDIA GPUs.Apache 2.0
mistral.rsmistral.rsBlazingly fast LLM inference.CPU, GPURust-based implementation, performance optimization, lightweight.MIT
NanoFlowNanoFlowThroughput-oriented high-performance serving framework for LLMs.CPU, GPUHigh throughput, low latency, optimized for large-scale deployments.Apache 2.0
[LMCache](https://gi