Darkness Chou
darknessc
AI & ML interests
None yet
Organizations
None yet
darknessc's activity
KeyError: 'model.layers.0.block_sparse_moe.experts.0.w1.g_idx' when running with tensor parallelism on vllm
1
#1 opened about 1 year ago
by
KronusCon
Can anyone tell me which parameters are suitable for deploying quantized models on the 4090?
#3 opened about 1 year ago
by
darknessc