Initial commit: obsidian to gitea
This commit is contained in:
20
phd/weekly-report/25/250720.md
Normal file
20
phd/weekly-report/25/250720.md
Normal file
@@ -0,0 +1,20 @@
|
||||
Objectives
|
||||
- MoE pattern feature
|
||||
- EP design for inference performance
|
||||
|
||||
Key Results
|
||||
- [6/10] Survey MoE works and their observations
|
||||
- [9/10] Analysis experts load balance's temporal locality
|
||||
- [4/10] Analysis correlations between MoE layers
|
||||
- [0/10] Understand how EP influence performance fully
|
||||
- [0/10] Verify how dynamic EP influence performance
|
||||
|
||||
Last Week
|
||||
- Survey the infrastructure of Bailian, specially in model serving and batching.
|
||||
- Give a KVCache cache talk in Ali w/ Jinbo.
|
||||
- Review 2 papers as shadow PC.
|
||||
- Survey the agent workflow for potential system problem.
|
||||
|
||||
Next Week
|
||||
- Survey the different parallelism setup scheduling.
|
||||
- Review and write comments for all assigned papers.
|
||||
Reference in New Issue
Block a user