4x — independent software & tools
-
1Cat-vLLM
Optimize Tesla V100 GPUs for AWQ 4-bit inference with improved speed, stability, and support for modern large models like Qwen3.5 and MoE.
Optimize Tesla V100 GPUs for AWQ 4-bit inference with improved speed, stability, and support for modern large models like Qwen3.5 and MoE.