
ppl.llm.serving
None
Stars: 126

ppl.llm.serving is a serving component for Large Language Models (LLMs) within the PPL.LLM system. It provides a server based on gRPC and supports inference for LLaMA. The repository includes instructions for prerequisites, quick start guide, model exporting, server setup, client usage, benchmarking, and offline inference. Users can refer to the LLaMA Guide for more details on using this serving component.
README:
ppl.llm.serving
is a part of PPL.LLM
system.
We recommend users who are new to this project to read the Overview of system.
ppl.llm.serving
is a serving based on ppl.nn for various Large Language Models(LLMs). This repository contains a server based on gRPC and inference support for LLaMA.
- Linux running on x86_64 or arm64 CPUs
- GCC >= 9.4.0
- CMake >= 3.18
- Git >= 2.7.0
- CUDA Toolkit >= 11.4. 11.6 recommended. (for CUDA)
- Rust & cargo >= 1.8.0. (for Huggingface Tokenizer)
Here is a brief tutorial, refer to LLaMA Guide for more details.
-
Installing Prerequisites(on Debian or Ubuntu for example)
apt-get install build-essential cmake git
-
Cloning Source Code
git clone https://github.com/openppl-public/ppl.llm.serving.git
-
Building from Source
./build.sh -DPPLNN_USE_LLM_CUDA=ON -DPPLNN_CUDA_ENABLE_NCCL=ON -DPPLNN_ENABLE_CUDA_JIT=OFF -DPPLNN_CUDA_ARCHITECTURES="'80;86;87'" -DPPLCOMMON_CUDA_ARCHITECTURES="'80;86;87'" -DPPL_LLM_ENABLE_GRPC_SERVING=ON
NCCL is required if multiple GPU devices are used.
We support Sync Decode feature (mainly for offline_inference), which means model forward and decode in the same thread. To enable this feature, compile with marco
-DPPL_LLM_SERVING_SYNC_DECODE=ON
. -
Exporting Models
Refer to ppl.pmx for details.
-
Running Server
./ppl_llm_server \ --model-dir /data/model \ --model-param-path /data/model/params.json \ --tokenizer-path /data/tokenizer.model \ --tensor-parallel-size 1 \ --top-p 0.0 \ --top-k 1 \ --max-tokens-scale 0.94 \ --max-input-tokens-per-request 4096 \ --max-output-tokens-per-request 4096 \ --max-total-tokens-per-request 8192 \ --max-running-batch 1024 \ --max-tokens-per-step 8192 \ --host 127.0.0.1 \ --port 23333
You are expected to give the correct values before running the server.
-
model-dir
: path of models exported by ppl.pmx. -
model-param-path
: params of models.$model_dir/params.json
. -
tokenizer-path
: tokenizer files forsentencepiece
.
-
-
Running client: send request through gRPC to query the model
./ppl-build/client_sample 127.0.0.1:23333
See tools/client_sample.cc for more details.
-
Benchmarking
./ppl-build/client_qps_measure --target=127.0.0.1:23333 --tokenizer=/path/to/tokenizer/path --dataset=tools/samples_1024.json --request_rate=inf
See tools/client_qps_measure.cc for more details.
--request_rate
is the number of request per second, and valueinf
means send all client request with no interval. -
Running inference offline:
./offline_inference \ --model-dir /data/model \ --model-param-path /data/model/params.json \ --tokenizer-path /data/tokenizer.model \ --tensor-parallel-size 1 \ --top-p 0.0 \ --top-k 1 \ --max-tokens-scale 0.94 \ --max-input-tokens-per-request 4096 \ --max-output-tokens-per-request 4096 \ --max-total-tokens-per-request 8192 \ --max-running-batch 1024 \ --max-tokens-per-step 8192 \ --host 127.0.0.1 \ --port 23333
See tools/offline_inference.cc for more details.
This project is distributed under the Apache License, Version 2.0.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for ppl.llm.serving
Similar Open Source Tools

ppl.llm.serving
ppl.llm.serving is a serving component for Large Language Models (LLMs) within the PPL.LLM system. It provides a server based on gRPC and supports inference for LLaMA. The repository includes instructions for prerequisites, quick start guide, model exporting, server setup, client usage, benchmarking, and offline inference. Users can refer to the LLaMA Guide for more details on using this serving component.

starcoder2-self-align
StarCoder2-Instruct is an open-source pipeline that introduces StarCoder2-15B-Instruct-v0.1, a self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. It generates instruction-response pairs to fine-tune StarCoder-15B without human annotations or data from proprietary LLMs. The tool is primarily finetuned for Python code generation tasks that can be verified through execution, with potential biases and limitations. Users can provide response prefixes or one-shot examples to guide the model's output. The model may have limitations with other programming languages and out-of-domain coding tasks.

llm-detect-ai
This repository contains code and configurations for the LLM - Detect AI Generated Text competition. It includes setup instructions for hardware, software, dependencies, and datasets. The training section covers scripts and configurations for training LLM models, DeBERTa ranking models, and an embedding model. Text generation section details fine-tuning LLMs using the CLM objective on the PERSUADE corpus to generate student-like essays.

ragflow
RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines deep document understanding with Large Language Models (LLMs) to provide accurate question-answering capabilities. It offers a streamlined RAG workflow for businesses of all sizes, enabling them to extract knowledge from unstructured data in various formats, including Word documents, slides, Excel files, images, and more. RAGFlow's key features include deep document understanding, template-based chunking, grounded citations with reduced hallucinations, compatibility with heterogeneous data sources, and an automated and effortless RAG workflow. It supports multiple recall paired with fused re-ranking, configurable LLMs and embedding models, and intuitive APIs for seamless integration with business applications.

melodisco
Melodisco is an AI music player that allows users to listen to music and manage playlists. It provides a user-friendly interface for music playback and organization. Users can deploy Melodisco with Vercel or Docker for easy setup. Local development instructions are provided for setting up the project environment. The project credits various tools and libraries used in its development, such as Next.js, Tailwind CSS, and Stripe. Melodisco is a versatile tool for music enthusiasts looking for an AI-powered music player with features like authentication, payment integration, and multi-language support.

llama.vscode
llama.vscode is a local LLM-assisted text completion extension for Visual Studio Code. It provides auto-suggestions on input, allows accepting suggestions with shortcuts, and offers various features to enhance text completion. The extension is designed to be lightweight and efficient, enabling high-quality completions even on low-end hardware. Users can configure the scope of context around the cursor and control text generation time. It supports very large contexts and displays performance statistics for better user experience.

VLM-R1
VLM-R1 is a stable and generalizable R1-style Large Vision-Language Model proposed for Referring Expression Comprehension (REC) task. It compares R1 and SFT approaches, showing R1 model's steady improvement on out-of-domain test data. The project includes setup instructions, training steps for GRPO and SFT models, support for user data loading, and evaluation process. Acknowledgements to various open-source projects and resources are mentioned. The project aims to provide a reliable and versatile solution for vision-language tasks.

node-llama-cpp
node-llama-cpp is a tool that allows users to run AI models locally on their machines. It provides pre-built bindings with the option to build from source using cmake. Users can interact with text generation models, chat with models using a chat wrapper, and force models to generate output in a parseable format like JSON. The tool supports Metal and CUDA, offers CLI functionality for chatting with models without coding, and ensures up-to-date compatibility with the latest version of llama.cpp. Installation includes pre-built binaries for macOS, Linux, and Windows, with the option to build from source if binaries are not available for the platform.

T-MAC
T-MAC is a kernel library that directly supports mixed-precision matrix multiplication without the need for dequantization by utilizing lookup tables. It aims to boost low-bit LLM inference on CPUs by offering support for various low-bit models. T-MAC achieves significant speedup compared to SOTA CPU low-bit framework (llama.cpp) and can even perform well on lower-end devices like Raspberry Pi 5. The tool demonstrates superior performance over existing low-bit GEMM kernels on CPU, reduces power consumption, and provides energy savings. It achieves comparable performance to CUDA GPU on certain tasks while delivering considerable power and energy savings. T-MAC's method involves using lookup tables to support mpGEMM and employs key techniques like precomputing partial sums, shift and accumulate operations, and utilizing tbl/pshuf instructions for fast table lookup.

aiohttp-client-cache
aiohttp-client-cache is an asynchronous persistent cache for aiohttp client requests, based on requests-cache. It is easy to use, customizable, and persistent, with several storage backends available, including SQLite, DynamoDB, MongoDB, DragonflyDB, and Redis.

Unity-MCP
Unity-MCP is an AI helper designed for game developers using Unity. It facilitates a wide range of tasks in Unity Editor and running games on any platform by connecting to AI via TCP connection. The tool allows users to chat with AI like with a human, supports local and remote usage, and offers various default AI tools. Users can provide detailed information for classes, fields, properties, and methods using the 'Description' attribute in C# code. Unity-MCP enables instant C# code compilation and execution, provides access to assets and C# scripts, and offers tools for proper issue understanding and project data manipulation. It also allows users to find and call methods in the codebase, work with Unity API, and access human-readable descriptions of code elements.

obs-localvocal
LocalVocal is a Speech AI assistant OBS Plugin that enables users to transcribe speech into text and translate it into any language locally on their machine. The plugin runs OpenAI's Whisper for real-time speech processing and prediction. It supports features like transcribing audio in real-time, displaying captions on screen, sending captions to files, syncing captions with recordings, and translating captions to major languages. Users can bring their own Whisper model, filter or replace captions, and experience partial transcriptions for streaming. The plugin is privacy-focused, requiring no GPU, cloud costs, network, or downtime.

FlexFlow
FlexFlow Serve is an open-source compiler and distributed system for **low latency**, **high performance** LLM serving. FlexFlow Serve outperforms existing systems by 1.3-2.0x for single-node, multi-GPU inference and by 1.4-2.4x for multi-node, multi-GPU inference.

ai-toolkit
The AI Toolkit by Ostris is a collection of tools for machine learning, specifically designed for image generation, LoRA (latent representations of attributes) extraction and manipulation, and model training. It provides a user-friendly interface and extensive documentation to make it accessible to both developers and non-developers. The toolkit is actively under development, with new features and improvements being added regularly. Some of the key features of the AI Toolkit include: - Batch Image Generation: Allows users to generate a batch of images based on prompts or text files, using a configuration file to specify the desired settings. - LoRA (lierla), LoCON (LyCORIS) Extractor: Facilitates the extraction of LoRA and LoCON representations from pre-trained models, enabling users to modify and manipulate these representations for various purposes. - LoRA Rescale: Provides a tool to rescale LoRA weights, allowing users to adjust the influence of specific attributes in the generated images. - LoRA Slider Trainer: Enables the training of LoRA sliders, which can be used to control and adjust specific attributes in the generated images, offering a powerful tool for fine-tuning and customization. - Extensions: Supports the creation and sharing of custom extensions, allowing users to extend the functionality of the toolkit with their own tools and scripts. - VAE (Variational Auto Encoder) Trainer: Facilitates the training of VAEs for image generation, providing users with a tool to explore and improve the quality of generated images. The AI Toolkit is a valuable resource for anyone interested in exploring and utilizing machine learning for image generation and manipulation. Its user-friendly interface, extensive documentation, and active development make it an accessible and powerful tool for both beginners and experienced users.

clearml-serving
ClearML Serving is a command line utility for model deployment and orchestration, enabling model deployment including serving and preprocessing code to a Kubernetes cluster or custom container based solution. It supports machine learning models like Scikit Learn, XGBoost, LightGBM, and deep learning models like TensorFlow, PyTorch, ONNX. It provides a customizable RestAPI for serving, online model deployment, scalable solutions, multi-model per container, automatic deployment, canary A/B deployment, model monitoring, usage metric reporting, metric dashboard, and model performance metrics. ClearML Serving is modular, scalable, flexible, customizable, and open source.

ai-containers
This repository contains Dockerfiles, scripts, yaml files, Helm charts, etc. used to scale out AI containers with versions of TensorFlow and PyTorch optimized for Intel platforms. Scaling is done with python, Docker, kubernetes, kubeflow, cnvrg.io, Helm, and other container orchestration frameworks for use in the cloud and on-premise.
For similar tasks

arena-hard-auto
Arena-Hard-Auto-v0.1 is an automatic evaluation tool for instruction-tuned LLMs. It contains 500 challenging user queries. The tool prompts GPT-4-Turbo as a judge to compare models' responses against a baseline model (default: GPT-4-0314). Arena-Hard-Auto employs an automatic judge as a cheaper and faster approximator to human preference. It has the highest correlation and separability to Chatbot Arena among popular open-ended LLM benchmarks. Users can evaluate their models' performance on Chatbot Arena by using Arena-Hard-Auto.

max
The Modular Accelerated Xecution (MAX) platform is an integrated suite of AI libraries, tools, and technologies that unifies commonly fragmented AI deployment workflows. MAX accelerates time to market for the latest innovations by giving AI developers a single toolchain that unlocks full programmability, unparalleled performance, and seamless hardware portability.

ai-hub
AI Hub Project aims to continuously test and evaluate mainstream large language models, while accumulating and managing various effective model invocation prompts. It has integrated all mainstream large language models in China, including OpenAI GPT-4 Turbo, Baidu ERNIE-Bot-4, Tencent ChatPro, MiniMax abab5.5-chat, and more. The project plans to continuously track, integrate, and evaluate new models. Users can access the models through REST services or Java code integration. The project also provides a testing suite for translation, coding, and benchmark testing.

long-context-attention
Long-Context-Attention (YunChang) is a unified sequence parallel approach that combines the strengths of DeepSpeed-Ulysses-Attention and Ring-Attention to provide a versatile and high-performance solution for long context LLM model training and inference. It addresses the limitations of both methods by offering no limitation on the number of heads, compatibility with advanced parallel strategies, and enhanced performance benchmarks. The tool is verified in Megatron-LM and offers best practices for 4D parallelism, making it suitable for various attention mechanisms and parallel computing advancements.

marlin
Marlin is a highly optimized FP16xINT4 matmul kernel designed for large language model (LLM) inference, offering close to ideal speedups up to batchsizes of 16-32 tokens. It is suitable for larger-scale serving, speculative decoding, and advanced multi-inference schemes like CoT-Majority. Marlin achieves optimal performance by utilizing various techniques and optimizations to fully leverage GPU resources, ensuring efficient computation and memory management.

MMC
This repository, MMC, focuses on advancing multimodal chart understanding through large-scale instruction tuning. It introduces a dataset supporting various tasks and chart types, a benchmark for evaluating reasoning capabilities over charts, and an assistant achieving state-of-the-art performance on chart QA benchmarks. The repository provides data for chart-text alignment, benchmarking, and instruction tuning, along with existing datasets used in experiments. Additionally, it offers a Gradio demo for the MMCA model.

Tiktoken
Tiktoken is a high-performance implementation focused on token count operations. It provides various encodings like o200k_base, cl100k_base, r50k_base, p50k_base, and p50k_edit. Users can easily encode and decode text using the provided API. The repository also includes a benchmark console app for performance tracking. Contributions in the form of PRs are welcome.

ppl.llm.serving
ppl.llm.serving is a serving component for Large Language Models (LLMs) within the PPL.LLM system. It provides a server based on gRPC and supports inference for LLaMA. The repository includes instructions for prerequisites, quick start guide, model exporting, server setup, client usage, benchmarking, and offline inference. Users can refer to the LLaMA Guide for more details on using this serving component.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.