https://pypi.org/project/eyestech-mla/ Recent updates to the Python Package Index for eyestech-mla en https://pypi.org/project/eyestech-mla/1.0.0/ DeepSeek Multi-Head Latent Attention (MLA) reference kernel with absorbed query decoding and KV cache memory scaling benchmarks. research@eyestech.in, research@eyestech.in Sun, 13 Sep 2026 16:49:03 GMT