Initial commit: obsidian to gitea
This commit is contained in:
22
phd/weekly-report/25/250622.md
Normal file
22
phd/weekly-report/25/250622.md
Normal file
@@ -0,0 +1,22 @@
|
||||
Objectives
|
||||
- Serverless KVCache cache
|
||||
- MoE pattern feature
|
||||
- EP design for inference performance
|
||||
|
||||
Key Results
|
||||
- [5/10] Prepare slides for ATC'25 presentation w/ Jinbo
|
||||
- [1/10] Survey MoE works and their observations
|
||||
- [9/10] Analysis experts load balance's temporal locality
|
||||
- [0/10] Analysis correlations between MoE layers
|
||||
- [0/10] Understand how EP influence performance fully
|
||||
- [0/10] Verify how dynamic EP influence performance
|
||||
|
||||
Last Week
|
||||
- Tracing expert pattern with Qwen trace under Qwen3-235B and DeepSeek-671B.
|
||||
- Analysis expert pattern's temporal locality in large models (Qwen3-235B and DeepSeek-671B).
|
||||
- Prepare KVCache slides.
|
||||
- All misc for graduation.
|
||||
|
||||
Next Week
|
||||
- Analysis the expert pattern's correlations between layers.
|
||||
- Survey current MoE works for more observations to check.
|
||||
Reference in New Issue
Block a user