| { |
| "name": "com.microsoft.GroupQueryAttention", |
| "id": "_com_microsoft_groupqueryattention_webgpu_1ea0022", |
| "version": 1, |
| "license": "Apache-2.0", |
| "backend": { "type": "webgpu" }, |
| "digest": { |
| "algorithm": "sha256", |
| "files": { |
| "attention-rank4-tiled.wgsl.jinja": "gYl58ecIVTxJJkvnK/6lNcbPKaRT24cfz5Yx0MxxxxE=", |
| "attn-flash-decode-splitk-merge.wgsl.jinja": "y3ubiijNd5rGJa2KVdluBdaoKYAGeqrPVd6KSppJPHw=", |
| "attn-flash-decode-splitk.wgsl.jinja": "xRRcDB3IGuE25xq3sG1qVPHRsESDmfA15KFVKlq5l4w=", |
| "attn-flash-online.wgsl.jinja": "ontnzJw9RHN7DklqqyavsAiRuKrsnWuEiU+vllbKfGE=", |
| "attn-flash-prefill-cluster.wgsl.jinja": "UHb5IdDeGHB/0gsQdAHcfg9FI73nyzk3zoZiIhaWbgI=", |
| "attn-flash-q32-broadcast.wgsl.jinja": "U/O9TNr3pXvFP+VZ2EAJLuXaWSz62De0TQEmEiU7TLc=", |
| "attn-materialized-rowstats-combine-f32.wgsl.jinja": "zcR02XUVlPyYeLeWH7gLOX65BcozZ1qje9hSIZSOaBA=", |
| "attn-materialized-sgmat-f32.wgsl.jinja": "rNruz2BmIcsQeu5eUnQZh41ftfDt/PjqnZiy2XT+9bk=", |
| "attn-online-scalar.wgsl.jinja": "AJGUYoMkrTHnwCPxu1gVp2CIrdHlca5PMgr9mgqukz4=", |
| "bench.json": "bUGLPxdrsT20K/2ptNbqVs+28i4d2W/9vOyPld+joKs=", |
| "gqa-attention.wgsl.jinja": "9JBHgllUq4dekL6Y1uXkyi2NoEYKjHTkHqnhktbgdzY=", |
| "gqa-present.wgsl.jinja": "/63mkauF/TKCsH4dxgIVlTZnREzSd/j64WGkvu6i2ls=", |
| "gqa-qprep.wgsl.jinja": "kRFlYxr5SdQJlbjmcF/Ii+0w56q0xhF8jyAOKPNx47I=", |
| "manifest.json": "U9Xgwr8xQCIMv/BNUNjiaMDyUjEVXkawKtl5Bsnn4UA=", |
| "test.json": "GGjXGSZThloU2mCpXKJf9lJVgddpxc8ouDX+JRD5zTs=" |
| } |
| }, |
| "provenance": { "kernel": { "sha": "91d990483a174128daf7673f3f37a7c890493ae1", "dirty": false } }, |
| "webgpu": { |
| "manifestSpec": "2.0", |
| "variants": { |
| "qkv_present_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_materialized_sgmat_f16": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_rotary_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja", "gqa-qprep.wgsl.jinja"], |
| "past_kv_rotary_materialized_sgmat_f16": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja", "gqa-qprep.wgsl.jinja"], |
| "new_kv_past_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "share_append_materialized_sgmat_f32": ["attn-materialized-rowstats-combine-f32.wgsl.jinja", "attn-materialized-sgmat-f32.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_share_append_split": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_share_append_headsink_split": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_share_append_rotary_split": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_tiled_nosg": ["attention-rank4-tiled.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash": ["attn-flash-online.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present": ["attn-online-scalar.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int8": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int4": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int8_decode_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_cluster": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_qnorm_rotary_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja", "gqa-qprep.wgsl.jinja"], |
| "quant_int8_decode_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_cluster_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_qnorm_rotary_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja", "gqa-qprep.wgsl.jinja"], |
| "past_kv_decode_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_past_decode_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_decode_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_decode_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_past_decode_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_decode_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_past_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_rotary_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_softcap_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_headsink_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_headsink_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_past_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_rotary_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_softcap_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_headsink_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_headsink_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_q32_broadcast": ["attn-flash-q32-broadcast.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "qkv_present_flash_q32_shared": ["attn-flash-q32-broadcast.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_rotary": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_qnorm_rotary": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_past": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "window_shift_append": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "new_kv_qnorm_rotary": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_headsink": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "past_kv_bias_headsink": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int8_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int4_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int8_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "quant_int4_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "share_append_split_decode_splitk": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "share_append_split_decode_splitk_nosg": ["attn-flash-decode-splitk-merge.wgsl.jinja", "attn-flash-decode-splitk.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "share_append_split_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], |
| "share_append_split_flash_prefill_nosg": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"] |
| } |
| } |
| } |
|
|