Tej PRO
cudaoom
ยท
AI & ML interests
None yet
Organizations
quantization script (not QAD)
1
#9 opened about 2 months ago
by
cudaoom
Availability of 7B and 14B models mentioned in the paper
๐ 3
1
#11 opened 3 months ago
by
Sopelllka
Has anybody got MTP working on VLLM? ('GPUModelRunner' object has no attribute 'drafter')
1
#36 opened 6 months ago
by
stev236
10,500 tok/sec fast apply - Morph
#1 opened 6 months ago
by
cudaoom