Constraints
- ntokens = sum(seqlen[i]), i=0, 1...batch-1.
- There are the following restrictions on the
Atlas inference products :- The compression function is not supported.
- If the data format is marked with NZ, the data format must be NZ.
- The dimensions of keyCache and valueCache must be [num_blocks, num_head*head_size/16, block_size, 16]. The last dimension must be 16, and block_size must be 16-aligned.
- When kvCacheCfg is set to K_CACHE_V_CACHE or K_CACHE_V_CACHE_NZ, the data format is NZ.
- head_size must be 32-byte aligned.
- If the last dimensions of the key and value are different, only
Atlas A2 training products /Atlas A2 inference products andAtlas A3 inference products /Atlas A3 training products are supported. In this scenario, keyCache, valueCache, keyCacheOut, and valueCacheOut support only the ND format. - The data types of key, value, keyCache, valueCache, keyCacheOut, and valueCacheOut must be the same.
- The data formats of keyCache, valueCache, keyCacheOut, and valueCacheOut must be the same.
- The single-input single-output function is supported only by the
Atlas A2 training products /Atlas A2 inference products andAtlas A3 inference products /Atlas A3 training products and does not support compression. - In the compression scenario, the cache size must be greater than the size after compression.
- If multi-head compression is disabled, the NZ format supports only the float16 data type on the
Atlas 200I/500 A2 inference products . - When the function of converting the format of the input to NZ is enabled, the following restrictions apply:
- Only
Atlas A2 training products /Atlas A2 inference products andAtlas A3 inference products /Atlas A3 training products are supported. - The length of key can be different from that of value. That is, the last dimension of key can be different from that of value.
- The data type of key can be different from that of value.
- Only
- When the multi-head compression function is enabled in the rope scenario, the value of head_size cannot exceed 16 × 1024.
Parent topic: ReshapeAndCacheOperation