Generates nonsense if running latest VLLM with Flashinfer 0.4
#7 opened 9 days ago
by
stev236
Availability on Vertex AI Model Garden
#6 opened 21 days ago
by
elliotdkim
Attempted to call `variable.set_data(tensor)`, but `variable` and `tensor` have incompatible tensor type.
#5 opened 24 days ago
by
dhyces
Finetune Granite 4.0 for Greek Language
1
#4 opened 26 days ago
by
myrulezzz
Quantization results in model not supporting Tensor Parallel mode.
#3 opened 26 days ago
by
stev236
Is it possible, to fine tune this model on rtx pro 6000?
1
#2 opened 26 days ago
by
win10
VLLM Support
3
#1 opened 27 days ago
by
jtvino