Open Issues Need Help
View All on GitHub GeGLU: fp64 gradcheck is deferred 19 days ago
enhancement good first issue
Forge-researchlab/forge-kernels Forge-researchlab/forge-kernels Forge kernels — fused Triton kernels for faster, leaner LLM fine-tuning. One-call patching into Hugging Face models via forge.patch(model), with FSDP2 multi-GPU support and a growing set of kernels and architectures. Every speedup backed by a committed benchmark. Apache-2.0.
Open project →
9
Forge kernels — fused Triton kernels for faster, leaner LLM fine-tuning. One-call patching into Hugging Face models via forge.patch(model), with FSDP2 multi-GPU support and a growing set of kernels and architectures. Every speedup backed by a committed benchmark. Apache-2.0.
Python
#cuda#fine-tuning#fsdp#gemma#gpu-kernels#gpu-optimization#huggingface#llm#lora#pytorch#qwen#transformers#triton