Large model computing 大模型计算 (80240832)

• Lecture 1: introduction (slides)

• Lecture 2: transformers (slides)

• Lecture 3: llms (slides)

• Lecture 8: quantization (slides)

• Lecture 9: quantized training (slides)

• Lecture 10: sparsity (slides)

• Lecture 11: MLA (slides)

• Lecture 12: sparse linear attention (slides)

• HW1 (zip)

• HW4 (pdf)

• HW5 (pdf)