Popular repositories Loading

1. 25ASPLOS-Medusa 25ASPLOS-Medusa Public

   Forked from thustorage/Medusa

   Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]

   HTML 12 1

2. 24MLSYS-prompt-cache 24MLSYS-prompt-cache Public

   Forked from yale-sys/prompt-cache

   Modular and structured prompt caching for low-latency LLM inference

   Python 9

3. 26FAST-PipeANN 26FAST-PipeANN Public

   Forked from thustorage/PipeANN

   A low-latency, billion-scale, and updatable graph-based vector store on SSD.

   Jupyter Notebook 8 5

4. 24PPOPP-Liger 24PPOPP-Liger Public

   C++ 5

5. 25Eurosys-NeuStream-AE 25Eurosys-NeuStream-AE Public

   Forked from Fjallraven-hc/NeuStream-AE

   Artifact Evaluation

   Python 4

6. Optimus-CC Optimus-CC Public

   [ASPLOS'23] Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression

   Python 3 4