Popular repositories Loading

1. nvtop nvtop Public

   Forked from Syllo/nvtop

   GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

   C 1

2. hipfire hipfire Public

   Forked from warpfront/hipfire

   RDNA-native LLM inference engine in Rust.

   Rust 1

3. vllm.cpp vllm.cpp Public

   Forked from localai-org/vllm.cpp

   a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (for example, RadixAttention, Cache-aware scheduling)

   C++

4. atlas atlas Public

   Forked from alesha-pro/atlas

   Interactive canvas for taking an LLM apart tensor by tensor: measured INT8/INT4/FP8 error, distributions, spectra and outlier channels for every weight tensor

   TypeScript

5. hindsight hindsight Public

   Forked from vectorize-io/hindsight

   Hindsight: Agent Memory That Learns

   Python

6. exllamav3-rocm exllamav3-rocm Public

   Forked from turboderp-org/exllamav3

   An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

   Python