EmbeddedLLM
Unleashing open-source LLM
Pinned
Repositories
Showing 10 of 11 repositories
-
-
- dspy Public Forked from stanfordnlp/dspy
DSPy: The framework for programming—not prompting—foundation models
- causal-conv1d-rocm Public Forked from Dao-AILab/causal-conv1d
Causal depthwise conv1d in CUDA, with a PyTorch interface
- EAGLE Public Forked from SafeAILab/EAGLE
EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation
-
- grouped_gemm-rocm Public Forked from tgale96/grouped_gemm
PyTorch bindings for CUTLASS grouped GEMM.
- xformers-rocm Public Forked from facebookresearch/xformers
Strip down to support flash attention v2 ROCM.
-