Roman Ageev

RomaA2000/dynamo

A Datacenter Scale Distributed Inference Serving Framework

RomaA2000/LMCache

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

RomaA2000/tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

RomaA2000/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

RomaA2000/daal4py

sources for daal4py - a convenient Python API to DAAL

RomaA2000/MountainCarContinuous

solutions for the MountainCar-v0 and MountainCarContinuous-v0

RomaA2000/YandexCup2020F

RomaA2000/chat.petals.dev

💬 Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client

RomaA2000/petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

RomaA2000/xTuring

Easily build, customize and control your own LLMs

RomaA2000/RecommendationSystems

RomaA2000/QuadraticSieve

RomaA2000/SDCourse

homework of software development course

RomaA2000/haskell

haskell course hw

RomaA2000/PGM-index

🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of items using orders of magnitude less space than traditional indexes

RomaA2000/some_cpp_programs

cpp programs

RomaA2000/svm_benchmarks

RomaA2000/scikit-learn_bench

Benchmark for optimizations to scikit-learn in the Intel Distribution for Python*

RomaA2000/JavaAdvanced

RomaA2000/tgnews

RomaA2000/Guns_and_Dungeons

ios game

RomaA2000/face_detecting

naural_face

RomaA2000/list

exam list

RomaA2000/vector_move

vector with move

RomaA2000/vector

vector with copy on write and small object optimization

RomaA2000/tuple

simple tuple implementation

RomaA2000/huffman

huffman encoder and decoder

RomaA2000/big_integer_copy_on_write

really big numbers with small object and copy on write optimizations

RomaA2000/big_integer

really big numbers

RomaA2000/itmo-java

my java homeworks