Pinned Repositories
Academic-project-page-template
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
AIpro1
AIpro1
AIpro2
AIpro2_v1.0
AIR_OS1.2
AIR_SCC_OS
for thu AIR_SCC 2020
MagicEnc
MagicPiG
Hybrid Attention for LLMs
quantum-ml
Sequoia2
dreaming-panda's Repositories
dreaming-panda/MagicEnc
dreaming-panda/MagicPiG
Hybrid Attention for LLMs
dreaming-panda/Sequoia2
dreaming-panda/DeepSpeedExamples
Example models using DeepSpeed
dreaming-panda/dreaming-panda.github.io
dreaming-panda/entropy
dreaming-panda/extension-cpp
C++ extensions in PyTorch
dreaming-panda/flash-attention
Fast and memory-efficient exact attention
dreaming-panda/flashinfer
FlashInfer: Kernel Library for LLM Serving
dreaming-panda/FlexSpec
dreaming-panda/gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
dreaming-panda/gqa-test
dreaming-panda/graph-inference
dreaming-panda/GRIFFIN
dreaming-panda/hack
dreaming-panda/icl
dreaming-panda/lab-page
dreaming-panda/lm-evaluation-harness
A framework for few-shot evaluation of language models.
dreaming-panda/lm_inference
dreaming-panda/LMBackend
dreaming-panda/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
dreaming-panda/meta
dreaming-panda/MTBench
dreaming-panda/Ruler
dreaming-panda/Sequoia-Official
scalable and robust tree-based speculative decoding algorithm
dreaming-panda/Sequoia_MT
dreaming-panda/Sequoia_Serving
dreaming-panda/Sirius
dreaming-panda/specdec
dreaming-panda/xFasterTransformer