benchmarks: ready for hybrid revised

This commit is contained in:
Per Stark
2025-12-03 11:38:07 +01:00
parent 2939e4c2a4
commit dd881efbf9
22 changed files with 760 additions and 476 deletions

176
Cargo.lock generated
View File

@@ -1929,13 +1929,22 @@ dependencies = [
"subtle",
]
[[package]]
name = "dirs"
version = "5.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "44c45a9d03d6676652bcb5e724c7e988de1acad23a711b5217ab9cbecbec2225"
dependencies = [
"dirs-sys 0.4.1",
]
[[package]]
name = "dirs"
version = "6.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c3e8aa94d75141228480295a7d0e7feb620b1a5ad9f12bc40be62411e38cce4e"
dependencies = [
"dirs-sys",
"dirs-sys 0.5.0",
]
[[package]]
@@ -1948,6 +1957,18 @@ dependencies = [
"dirs-sys-next",
]
[[package]]
name = "dirs-sys"
version = "0.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "520f05a5cbd335fae5a99ff7a6ab8627577660ee5cfd6a94a6a929b52ff0321c"
dependencies = [
"libc",
"option-ext",
"redox_users 0.4.6",
"windows-sys 0.48.0",
]
[[package]]
name = "dirs-sys"
version = "0.5.0"
@@ -2159,6 +2180,9 @@ name = "esaxx-rs"
version = "0.1.10"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d817e038c30374a4bcb22f94d0a8a0e216958d4c3dcde369b1439fec4bdda6e6"
dependencies = [
"cc",
]
[[package]]
name = "euclid"
@@ -2198,6 +2222,7 @@ dependencies = [
"tokio",
"tracing",
"tracing-subscriber",
"unicode-normalization",
"uuid",
]
@@ -2278,12 +2303,12 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d2e9bf3ea201e5d338450555088e02cff23b00be92bead3eff7ed341c68f5ac6"
dependencies = [
"anyhow",
"hf-hub",
"hf-hub 0.4.3",
"image",
"ndarray 0.16.1",
"ort",
"serde_json",
"tokenizers",
"tokenizers 0.22.1",
]
[[package]]
@@ -2808,13 +2833,30 @@ version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
[[package]]
name = "hf-hub"
version = "0.3.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b780635574b3d92f036890d8373433d6f9fc7abb320ee42a5c25897fc8ed732"
dependencies = [
"dirs 5.0.1",
"indicatif",
"log",
"native-tls",
"rand 0.8.5",
"serde",
"serde_json",
"thiserror 1.0.69",
"ureq",
]
[[package]]
name = "hf-hub"
version = "0.4.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "629d8f3bbeda9d148036d6b0de0a3ab947abd08ce90626327fc3547a49d59d97"
dependencies = [
"dirs",
"dirs 6.0.0",
"http",
"indicatif",
"libc",
@@ -3337,6 +3379,7 @@ dependencies = [
"surrealdb",
"tempfile",
"text-splitter",
"tokenizers 0.20.4",
"tokio",
"tracing",
"url",
@@ -4986,6 +5029,17 @@ dependencies = [
"syn 1.0.109",
]
[[package]]
name = "pulldown-cmark"
version = "0.12.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f86ba2052aebccc42cbbb3ed234b8b13ce76f75c3551a303cb2bcffcff12bb14"
dependencies = [
"bitflags 2.9.0",
"memchr",
"unicase",
]
[[package]]
name = "pxfm"
version = "0.1.25"
@@ -5251,6 +5305,17 @@ dependencies = [
"rayon-core",
]
[[package]]
name = "rayon-cond"
version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "059f538b55efd2309c9794130bc149c6a553db90e9d99c2030785c82f0bd7df9"
dependencies = [
"either",
"itertools 0.11.0",
"rayon",
]
[[package]]
name = "rayon-cond"
version = "0.4.0"
@@ -6746,9 +6811,11 @@ dependencies = [
"either",
"itertools 0.13.0",
"once_cell",
"pulldown-cmark",
"regex",
"strum",
"thiserror 1.0.69",
"tokenizers 0.20.4",
"unicode-segmentation",
]
@@ -6908,6 +6975,39 @@ version = "0.1.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20"
[[package]]
name = "tokenizers"
version = "0.20.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3b08cc37428a476fc9e20ac850132a513a2e1ce32b6a31addf2b74fa7033b905"
dependencies = [
"aho-corasick",
"derive_builder",
"esaxx-rs",
"getrandom 0.2.16",
"hf-hub 0.3.2",
"indicatif",
"itertools 0.12.1",
"lazy_static",
"log",
"macro_rules_attribute",
"monostate",
"onig",
"paste",
"rand 0.8.5",
"rayon",
"rayon-cond 0.3.0",
"regex",
"regex-syntax 0.8.5",
"serde",
"serde_json",
"spm_precompiled",
"thiserror 1.0.69",
"unicode-normalization-alignments",
"unicode-segmentation",
"unicode_categories",
]
[[package]]
name = "tokenizers"
version = "0.22.1"
@@ -6929,7 +7029,7 @@ dependencies = [
"paste",
"rand 0.9.1",
"rayon",
"rayon-cond",
"rayon-cond 0.4.0",
"regex",
"regex-syntax 0.8.5",
"serde",
@@ -7919,6 +8019,15 @@ dependencies = [
"windows-link 0.1.1",
]
[[package]]
name = "windows-sys"
version = "0.48.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "677d2418bec65e3338edb076e806bc1ec15693c5d0104683f2efe857f61056a9"
dependencies = [
"windows-targets 0.48.5",
]
[[package]]
name = "windows-sys"
version = "0.52.0"
@@ -7946,6 +8055,21 @@ dependencies = [
"windows-targets 0.53.5",
]
[[package]]
name = "windows-targets"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
dependencies = [
"windows_aarch64_gnullvm 0.48.5",
"windows_aarch64_msvc 0.48.5",
"windows_i686_gnu 0.48.5",
"windows_i686_msvc 0.48.5",
"windows_x86_64_gnu 0.48.5",
"windows_x86_64_gnullvm 0.48.5",
"windows_x86_64_msvc 0.48.5",
]
[[package]]
name = "windows-targets"
version = "0.52.6"
@@ -7979,6 +8103,12 @@ dependencies = [
"windows_x86_64_msvc 0.53.0",
]
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
[[package]]
name = "windows_aarch64_gnullvm"
version = "0.52.6"
@@ -7991,6 +8121,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "86b8d5f90ddd19cb4a147a5fa63ca848db3df085e25fee3cc10b39b6eebae764"
[[package]]
name = "windows_aarch64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
[[package]]
name = "windows_aarch64_msvc"
version = "0.52.6"
@@ -8003,6 +8139,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c7651a1f62a11b8cbd5e0d42526e55f2c99886c77e007179efff86c2b137e66c"
[[package]]
name = "windows_i686_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
[[package]]
name = "windows_i686_gnu"
version = "0.52.6"
@@ -8027,6 +8169,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9ce6ccbdedbf6d6354471319e781c0dfef054c81fbc7cf83f338a4296c0cae11"
[[package]]
name = "windows_i686_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
[[package]]
name = "windows_i686_msvc"
version = "0.52.6"
@@ -8039,6 +8187,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "581fee95406bb13382d2f65cd4a908ca7b1e4c2f1917f143ba16efe98a589b5d"
[[package]]
name = "windows_x86_64_gnu"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
[[package]]
name = "windows_x86_64_gnu"
version = "0.52.6"
@@ -8051,6 +8205,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2e55b5ac9ea33f2fc1716d1742db15574fd6fc8dadc51caab1c16a3d3b4190ba"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
[[package]]
name = "windows_x86_64_gnullvm"
version = "0.52.6"
@@ -8063,6 +8223,12 @@ version = "0.53.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0a6e035dd0599267ce1ee132e51c27dd29437f63325753051e71dd9e42406c57"
[[package]]
name = "windows_x86_64_msvc"
version = "0.48.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
[[package]]
name = "windows_x86_64_msvc"
version = "0.52.6"