Skip to content

speedup the inference of vit (gelu, rmsnorm and fa3 for H-series) and chunked prefill for multimodal #815

speedup the inference of vit (gelu, rmsnorm and fa3 for H-series) and chunked prefill for multimodal

speedup the inference of vit (gelu, rmsnorm and fa3 for H-series) and chunked prefill for multimodal #815