Popular repositories Loading

1. ESPN-v1 ESPN-v1 Public

   ESPN: Embedding from Storage Pipelined Network. GDS implementation for multi-vector embedding retrieval and bindings.

   C++ 13 1

2. Polar-Sparsity Polar-Sparsity Public

   Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity

   Python 6

3. SmartLife-Agent SmartLife-Agent Public

   Plan your life and get the upper hand with SmartLife Agent

   Python 5

4. Sentiment-Analysis Sentiment-Analysis Public

   Sentiment analysis comparisons between Naive Bayes, Perceptron, and BERT.

   Python 1

5. vllm-distributed vllm-distributed Public

   A high-throughput and memory-efficient inference and serving engine for LLMs. Distributed inference architecture added for multi-node multi-GPU inference.

   Python 1

6. cpp_kernels- cpp_kernels- Public

   C++