Alon Sokolovski
alonsoko
AI & ML interests
None yet
Organizations
None yet
43.1 tok/s for 2x DGX Spark Cluster
3
#1 opened 2 months ago
by
celikburak
AWQ or GPTQ (INT4) Quantization Planned?
#2 opened 2 months ago
by
alonsoko
BF16 or FP8/FP4 mixed .safetensors version?
1
#3 opened 3 months ago
by
aabbccddwasd
KL Divergence
➕ 3
2
#1 opened 4 months ago
by
alonsoko
quant fails to load in VLLM due to vision tower?
2
#1 opened 4 months ago
by
jpbwin
quant fails to load in VLLM due to vision tower?
2
#1 opened 4 months ago
by
jpbwin
quant fails to load in VLLM due to vision tower?
2
#1 opened 4 months ago
by
jpbwin