Pinned Loading

1. vllm-project/vllm vllm-project/vllm Public

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

   Python 86.7k 19.6k

2. vllm-project/llm-compressor vllm-project/llm-compressor Public

   Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

   Python 3.6k 580

3. OlmoEarth-Agent OlmoEarth-Agent Public

   Agent for OlmoEarth Studio

   Python 3

4. ECCO-DarwinDiff ECCO-DarwinDiff Public

   A differentiable PyTorch reimplementation of ECCO-Darwin ocean biogeochemistry

   Python

5. Quantization-and-Benchmarks Quantization-and-Benchmarks Public

   A comprehensive evaluation of quantization methods for LLM models, comparing BF16, FP8, and FP4 precision formats.

   Python

6. nano-LMcache nano-LMcache Public

   A minimal, readable prefix cache for LLM serving (a nano-LMCache): chunk hashing + LRU CPU KV store + model-aware KV geometry. Runs on CPU.

   Python 1