[Question]请问这里的有关grid norm的计算逻辑有什么理论指导吗?
Open
- Dominant language
- Python
- Stars
- 8.1k
- Forks
- 748
- Avg merge
- 6d 2h
- Merged PRs (30d)
- 54
Description
请问这里https://github.com/InternLM/lmdeploy/blob/e96e2b4ce0f484818611962eb128f2bbb22896c2/src/turbomind/kernels/gemm_s_f16/gemm_s4_f16_kernel.h#L83有关grid norm的计算有什么依据吗?
Contributor guide
Assessment
This issue has not been assessed yet.