gmlwns2000

sharkshark-4k

Upscale Twitch stream and restream into Twitch or RTMP or File.

sea-attention

Official Implementation of SEA: Sparse Linear Attention with Estimated Attention Mask (ICLR 2024)

streaming-llm-triton

OpenAI Triton Implementation of Streaming LLM

sttabt

[ICLR2023] Official code of Sparse Token Transformer with Attention Back-Tracking

hss001-latex-template

mlai-cli

hip-ainl

cs454-project

CS454 2023 F Team 4

InfiniGen

InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)

pypareto-native

Numba optimized version of `pypareto`. Sorting chains for pareto frontier extraction

RULER-hip

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

ai-fact-check-accuracy

cascading_kv_cache

EXAONE-3.5

Official repository for EXAONE 3.5 built by LG AI Research

gmlwns2000

gmlwns2000.github.io

AcadHomepage: A Modern and Responsive Academic Personal Homepage

hip-attention

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

hpc

image-augmentation-server

image-lm

InfiniteBench-hip

Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718

llmperf-hip

lm-evaluation-harness

A framework for few-shot evaluation of language models.

loft-hip

LOFT: A 1 Million+ Token Long-Context Benchmark

LongBench-hip

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

LongLM

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

sglang-hip12

SGLang is a fast serving framework for large language models and vision language models. See hip12-offload-add-offload-cache

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

triton-fix-autotune

Development repository for the Triton language and compiler

vllm-timber

A high-throughput and memory-efficient inference and serving engine for LLMs