ccx1324andClaude Opus 4.7 a5678c9185 fix: create LoRA parameters on base weight device instead of CPU ...

When `inject_lora()` replaces Linear layers with LoRALinear after the model
has been moved to CUDA, the new lora_A and lora_B parameters were always
created on CPU, causing a device mismatch error during the forward pass.

Now lora_A and lora_B are created on the same device and dtype as the
parent weight, matching the model's current device.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-07-20 16:11:48 +08:00

..

__init__.py

refactor: 拆分 module.py 为 components 子包

2026-05-15 20:08:36 +08:00

attention.py

perf: replace paged KV cache with contiguous ContiguousCache, decode all groups

2026-07-05 11:34:36 +08:00

decoder_block.py

perf: replace paged KV cache with contiguous ContiguousCache, decode all groups

2026-07-05 11:34:36 +08:00

embedding.py

refactor : neftune_alpha 在 Embedding 构造时传入，由模型配置链路负责

2026-06-19 14:23:27 +08:00

linear.py

feat : GPT-2 residual scaling weight init

2026-06-25 15:08:31 +08:00

lora.py

fix: create LoRA parameters on base weight device instead of CPU

2026-07-20 16:11:48 +08:00

mlp.py

feat : GPT-2 residual scaling weight init

2026-06-25 15:08:31 +08:00

norm.py

refactor: 拆分 module.py 为 components 子包

2026-05-15 20:08:36 +08:00

rope.py

feat: 新增NTK-Aware RoPE缩放支持

2026-05-25 21:22:07 +08:00