Skip to content

Commit

Permalink
[WeeklyReport] yinfan98 2024.04.19~2024.05.24 (#268)
Browse files Browse the repository at this point in the history
Co-authored-by: 尹帆 <yinfan@yinfandeMacBook-Pro.local>
Co-authored-by: Yuanle Liu <yuanlehome@163.com>
Co-authored-by: yinfan.1024 <yinfan.1024@bytedance.com>
  • Loading branch information
4 people authored Jul 9, 2024
1 parent be6bc87 commit b58ccc3
Show file tree
Hide file tree
Showing 2 changed files with 25 additions and 0 deletions.
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
### 姓名
尹帆
### 实习项目
推理 Pass & 融合算子优化
### 本周工作

1. 实现weight_quantize weight_only_int4 gpu kernel
2. 实现weight_only_int4 转置+重排kernel
3. kernel精度对齐

### 下周工作

1. Llama3 相关kernel
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
### 姓名
尹帆
### 实习项目
推理 Pass & 融合算子优化
### 本周工作

1. 实现RoPE算子支持 theta
2. 实现block multihead attention支持 GQA

### 下周工作

1. 推理模型实现任务

0 comments on commit b58ccc3

Please sign in to comment.