-
Notifications
You must be signed in to change notification settings - Fork 72
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[WeeklyReport] yinfan98 2024.04.19~2024.05.24 (#268)
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
1 parent
be6bc87
commit b58ccc3
Showing
2 changed files
with
25 additions
and
0 deletions.
There are no files selected for viewing
13 changes: 13 additions & 0 deletions
13
WeeklyReports/Hackathon_6th/23_yinfan98/[WeeklyReports]2024.04.19~2024.05.10.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |
12 changes: 12 additions & 0 deletions
12
WeeklyReports/Hackathon_6th/23_yinfan98/[WeeklyReports]2024.05.11~2024.05.24.md
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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 |