17 lines
687 B
Markdown
17 lines
687 B
Markdown
Objective
|
|
- Serverless KVCache cache
|
|
- DeepSeek deployment study
|
|
|
|
Key Results
|
|
- Refine some trace figures in 24h trace
|
|
- Give a cache policy evaluation method (w/ Jinbo)
|
|
- Survey the hardware for MoE deploying in medium-scale cluster
|
|
|
|
Last Week
|
|
- Finish all the trace clean and preprocess and re-plot some figures for traceA and traceB in new trace.
|
|
- Communicate with Jinbo to have a better understand in the gap between vLLM cache management and traditional cache policy. Figure out a evaluation method to judge the cache policy.
|
|
- Calculate the FLOPs requirement for DeepSeek.
|
|
|
|
Next Week
|
|
- Test and refine the cache policy.
|
|
- Try to summary the challenges for medium-scale deployment. |