cheng cheng
Results
4
issues of
cheng cheng
增加可复现的测评页面,在 LiBai 的代码仓库里,并增加索引。
- [x] Part 0 : Logical Chain 使用 LogicalChainPass 在 Job 层级进行内存复用的 chain merge 操作 - [x] Part 1 : AfterGradAccChain ,将 GradAcc 之后的子图合并为一个 logical chain - [x] Part 2...
enhancement
graph
### 🚀 The feature, motivation and pitch DeepSeek-V2 design **MLA (Multi-head Latent Attention)**, which utilizes low-rank key-value union compression to eliminate the bottleneck of inference-time key-value cache, thus supporting efficient...
feature request