Alexander Korolev
3dde0688ae
docker-images: glm52-nf3-hybrid
|
4 hete | |
|---|---|---|
| .. | ||
| b12x | 4 hete | |
| vllm | 4 hete | |
| hybrid.pth | 4 hete | |
| hybrid_loader.py | 4 hete | |
| mxfp8_tier.json | 4 hete | |
| nf3_kernel.py | 4 hete | |
| nf3_replan.py | 4 hete | |
| nvfp4_kernel.py | 4 hete | |
|
Alexander Korolev
3dde0688ae
docker-images: glm52-nf3-hybrid
|
4 hete | |
|---|---|---|
| .. | ||
| b12x | 4 hete | |
| vllm | 4 hete | |
| hybrid.pth | 4 hete | |
| hybrid_loader.py | 4 hete | |
| mxfp8_tier.json | 4 hete | |
| nf3_kernel.py | 4 hete | |
| nf3_replan.py | 4 hete | |
| nvfp4_kernel.py | 4 hete | |