Popular repositories Loading

1. GCCG GCCG Public

   Global Computation combining CPU and GPU

   5

2. FRIC FRIC Public

   Fast Recovery for LLM Inference Crash

   Python 1

3. buddy-mlir buddy-mlir Public

   Forked from buddy-compiler/buddy-mlir

   An MLIR-based compiler framework bridges DSLs (domain-specific languages) to DSAs (domain-specific architectures).

   C++

4. libtriton_jit libtriton_jit Public

   Forked from flagos-ai/libtriton_jit

   A Triton JIT runtime and ffi provider in C++

   C++

5. Albatross Albatross Public

   Forked from BlinkDL/Albatross

   Efficient RWKV inference engine. RWKV7 7.2B fp16 decoding 10250 tps @ single 5090.

   Python

6. FlagGems FlagGems Public

   Forked from flagos-ai/FlagGems

   FlagGems is an operator library for large language models implemented in the Triton Language.

   Python