nicolas pacheco
pachePizza
AI & ML interests
None yet
Organizations
None yet
Not working in VLLM
3
#1 opened 2 months ago
by
pachePizza
Error KeyError: 'layers.0.experts.0.down_proj.input_global_scale' when running on vllm
1
#5 opened 2 months ago
by
pachePizza
About quantization
4
#1 opened 3 months ago
by
pachePizza
Only producing garbage in H200, cu130 with CUDA 13.0
4
#1 opened 4 months ago
by
Dsturb
Can not run in llm-compresor
3
#1 opened 3 months ago
by
pachePizza
Can not run in llm-compresor
3
#1 opened 3 months ago
by
pachePizza