Download build/webgpu/metadata.json from webgpu-kernels/com.microsoft.GroupQueryAttention: direct link, hf CLI and curl.
- Browser
- Download file 8.1 kB
-
https://huggingface.co/kernels/webgpu-kernels/com.microsoft.GroupQueryAttention/resolve/v1/build/webgpu/metadata.json
- Command line
-
hf download hf://webgpu-kernels/com.microsoft.GroupQueryAttention@v1/build/webgpu/metadata.json
-
curl -L -o metadata.json https://huggingface.co/kernels/webgpu-kernels/com.microsoft.GroupQueryAttention/resolve/v1/build/webgpu/metadata.json
8.1 kB
| { | |
| "name": "com.microsoft.GroupQueryAttention", | |
| "id": "_com_microsoft_groupqueryattention_webgpu_0c84e3e", | |
| "version": 1, | |
| "license": "Apache-2.0", | |
| "backend": { "type": "webgpu" }, | |
| "digest": { | |
| "algorithm": "sha256", | |
| "files": { | |
| "attention-rank4-tiled.wgsl.jinja": "084x5bbpxeFR95/Q4nGzLrLnk9JJrd9XA1KJHxwU9CY=", | |
| "attn-flash-decode-splitk-merge.wgsl.jinja": "nKMUcaMP7mcKykLHoGsn/KnsIaJiJRHDsceE7dKVcwo=", | |
| "attn-flash-decode-splitk.wgsl.jinja": "ZD6C2fn5I7xZvvpTlsHdLtai8JBK2Ar+xc0SrLn3SAE=", | |
| "attn-flash-online.wgsl.jinja": "QGaUiZyIJuQ9xS00I8cuZWYQI8bGldV+UJ0Mp/5kj6w=", | |
| "attn-flash-prefill-cluster.wgsl.jinja": "Q7DUmulv66HOVBMkAannNVhEtOWkD+uhDn5muWo4p+E=", | |
| "attn-flash-q32-broadcast.wgsl.jinja": "vogUJggIxK8tRg2tDORhIXZLheesY3Y221iVFFyHVY4=", | |
| "attn-materialized-rowstats-combine-f32.wgsl.jinja": "SG+V1o5KhJ1LvkUQL0jcq62C+ETRGpy0XV9tvvOQivk=", | |
| "attn-materialized-sgmat-f32.wgsl.jinja": "R0+zNbbnfRKpA+R7lcgY5FPlkmLNzNBJwJe1PmaSOvE=", | |
| "attn-online-scalar.wgsl.jinja": "ysj3CuuKeu+MPlnaTwnNvCu3sSf8egjHE/uhE/Essmo=", | |
| "bench.json": "v06hV3rz9UPzelx7YbIHmyOWgbj/0Y9ci7iz9mQS6m0=", | |
| "gqa-attention.wgsl.jinja": "Wy1oR/7g/EzxQZizt/zGtOh4qiD60SVN4pfLSjmfsDo=", | |
| "gqa-present.wgsl.jinja": "r0ELXXscqaVYqTYzA9IYr/xl9jWAe20ZFPScyiw34UQ=", | |
| "gqa-qprep.wgsl.jinja": "VI/IHqwEMTpvrhFza3kKRDuLO3Eau91C4aMZRW0nAjg=", | |
| "manifest.json": "8m8RL1h3mBW9P8voV+gr/KpJiMheynqdWWhmcrOoi8E=", | |
| "test.json": "I771sUbwb/9MXIc27bUlvNl3UsiiFxP3H0/wRMt/B9M=" | |
| } | |
| }, | |
| "provenance": { "kernel": { "sha": "6fdf6301e2bbcc2f03bf1eaf493b7ad55ef33afc", "dirty": false } }, | |
| "webgpu": { | |
| "manifestSpec": "2.1", | |
| "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"], | |
| "new_kv_share_append_bidirectional_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_flash_causal": ["attn-flash-online.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "qkv_present": ["attn-online-scalar.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "qkv_present_causal": ["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"], | |
| "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_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"], | |
| "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"], | |
| "window_shift_rotary_append": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "window_shift_rotary_headsink_append": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "window_shift_rotary_bias_append": ["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"], | |
| "window_shift_headsink_append": ["gqa-attention.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "window_shift_bias_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"], | |
| "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_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"], | |
| "share_append_bidirectional_flash_prefill": ["attn-flash-prefill-cluster.wgsl.jinja", "gqa-present.wgsl.jinja"] | |
| } | |
| } | |
| } | |