mirror of
https://github.com/deepseek-ai/DeepGEMM
synced 2025-06-26 23:15:49 +00:00
Add a TODO
This commit is contained in:
parent
159ba93ab3
commit
5373da7b28
@ -19,7 +19,7 @@ Despite its lightweight design, DeepGEMM's performance matches or exceeds expert
|
|||||||
- [x] Fix TMA multicast compatibility for indivisible shapes
|
- [x] Fix TMA multicast compatibility for indivisible shapes
|
||||||
- [ ] Skip useless computation on M
|
- [ ] Skip useless computation on M
|
||||||
- [x] NVRTC as a faster compiler
|
- [x] NVRTC as a faster compiler
|
||||||
- [ ] Fully remove NVCC compilation
|
- [ ] Stolen JIT cache
|
||||||
- [ ] Sanitizer for testing
|
- [ ] Sanitizer for testing
|
||||||
- [ ] Weight gradient kernels for dense models
|
- [ ] Weight gradient kernels for dense models
|
||||||
- [ ] Weight gradient kernels for MoE models
|
- [ ] Weight gradient kernels for MoE models
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user