flash-attention 32 llm 12 flash-attention-2 7 pytorch 6 cuda 5 large-language-models 5 transformer 5 deep-learning 5 attention 5 nlp 4 large-language-model 4 tensor-cores 3 gpu-computing 3 artificial-intelligence 3 inference 3 pretrained-models 3 transformers 3 mla 3 gpu 3 deepseek-v3 3 deepseek 3 llm-training 2 nvidia 2 chinese 2 deepseek-r1 2 chatbot 2 multi-head-attention 2 mha 2 machine-learning 2 hpc 2 conda 2 attention-mechanism 2 llama2 2 rlhf 2 flash-attention-3 2 flash-mla 2 llm-inference 2 minimax-01 2 paged-attention 2 deepspeed 2 tensorrt-llm 2 vllm 2 deel-learning 2 glsl 2 gpu-acceleration 2 vulkan 2 jax 2 cuda-kernels 2 natural-language-processing 2 ring-attention 2 cpp 1 cross-platform 1 framework 1 qt 1 qwik-city 1 tailwind 1 typing-game 1 typing-practice 1 long-context 1 amdgpu 1 gpgpu 1 julia 1 clip 1 contrastive-learning 1 infinite-batch-size 1 memory-efficient 1 ai-safety 1 alternating-attention 1 fine-tuning 1 huggingface-transformers 1 modernbert 1 prompt-guard 1 fineweb 1 flax 1 gpt2 1 perceiver 1 vision-language-model 1 mi300x 1 rocm 1 amd-mi300 1 axolotl 1 pytorch-rocm 1 slurm 1 torch 1 triton 1 triton-lang 1 graphcore 1 ipu 1 poplar 1 gradient-checkpointing 1 code-generation 1 efficient 1 finetuning 1 vue 1 web 1 cutlass 1 tensor-core 1 bitnet 1 jupyter-notebook 1 low-rank-adaptation 1