dev
an archive of posts in this category
| May 11, 2026 | TRL sequence packing → DeepSeek MLA: 누락된 cu_seqlens 복원 |
|---|---|
| May 10, 2026 | MLA 학습 시 modeling-side projection fusion: q_a/kv_a 배치 + K-side absorption |
| May 10, 2026 | DeepSeek 계열 MoE 학습 가속: Python expert loop → grouped GEMM |
| Apr 11, 2026 | LLM 엔지니어가 알아야 할 GPU 아키텍처: Ampere → Hopper → Blackwell |
| Dec 03, 2023 | Keras 3.0 설명 |
| Feb 28, 2023 | Jetson Nano Tensorrt 적용 |
| Feb 24, 2023 | error: command 'aarch64-linux-gnu-gcc' failed with exit status 1 |
| Feb 12, 2023 | Jetson nano Ubuntu 20.04 (우분투 20.04) 설치 |
| Jul 13, 2022 | Quantization과 inference speed |
| Jul 12, 2022 | Pytorch Tensorrt 적용 |
| Jul 11, 2022 | Pytorch Quantization 적용 |
| Jan 10, 2021 | [Python] 우선순위 큐 (heapq vs priority queue) |