39 lines
920 B
Markdown
39 lines
920 B
Markdown
if sent_method not in [
|
||
+ "determine_num_available_blocks",
|
||
+ "initialize_cache",
|
||
+ ]:
|
||
|
||
|
||
|
||
ray 2.46.0 -> 2.47.1
|
||
ipconfig -a
|
||
|
||
`VLLM_USE_PRECOMPILED=1 pip install --editable .`
|
||
|
||
|
||
```
|
||
[Credentials]
|
||
language=EN
|
||
endpoint=oss-cn-hangzhou.aliyuncs.com
|
||
accessKeyID=LTAIJO7wLG9y8KJH
|
||
accessKeySecret=nbx8fIu9B94JoICuKRBhxfSQsMgYeY
|
||
```
|
||
|
||
|
||
---
|
||
|
||
基于 Qwen3-30B（128 experts, 48 layers, activate 8 experts）的测试来看：
|
||
- 每一层的 expert activation 并没有做到负载均衡，std/mean 的值都接近 1
|
||
- 最后几层的 std 明显比前面层的 std 大
|
||
|
||
|
||
|
||
TBD
|
||
- [ ] 不同 workload 的 expert activation 是否有显著区别
|
||
- [ ] 相邻层的 expert activation 是否有关联
|
||
- [ ] temporal pattern 和全局的关联
|
||
- [ ] 理解 EP 浴盆曲线
|
||
- [ ] 列个表，survey 现有工作的 points，和我们测试的对比
|
||
- [ ] reasoning 与 non reasoning 在同一个 session 混合
|
||
|