Skip to content

[TRANSFORMATIONS] SDPAToPagedAttention transformation: support decompression case in the Qwen-7b-Chat pattern #5506

[TRANSFORMATIONS] SDPAToPagedAttention transformation: support decompression case in the Qwen-7b-Chat pattern

[TRANSFORMATIONS] SDPAToPagedAttention transformation: support decompression case in the Qwen-7b-Chat pattern #5506