shangshng

Pinned Repositories

vllm
vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
Language:Python89 2 135
axolotl
merge medusa
Language:Python1 0 00
Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Language:Jupyter Notebook0 0 00
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Language:Python32.6k 268 5.7k5k

shangshng's Repositories

shangshng/axolotl
merge medusa
Language:Python1 0 00
shangshng/Medusa
Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads
Language:Jupyter Notebook0 0 00