hf_text-generation-inference/flake.lock

964 lines
26 KiB
Plaintext
Raw Normal View History

{
"nodes": {
"cachix": {
"inputs": {
"devenv": [
"crate2nix"
],
"flake-compat": [
"crate2nix"
],
"nixpkgs": "nixpkgs",
"pre-commit-hooks": [
"crate2nix"
]
},
"locked": {
"lastModified": 1709700175,
"narHash": "sha256-A0/6ZjLmT9qdYzKHmevnEIC7G+GiZ4UCr8v0poRPzds=",
"owner": "cachix",
"repo": "cachix",
"rev": "be97b37989f11b724197b5f4c7ffd78f12c8c4bf",
"type": "github"
},
"original": {
"owner": "cachix",
"ref": "latest",
"repo": "cachix",
"type": "github"
}
},
"cachix_2": {
"inputs": {
"devenv": [
"crate2nix",
"crate2nix_stable"
],
"flake-compat": [
"crate2nix",
"crate2nix_stable"
],
"nixpkgs": "nixpkgs_2",
"pre-commit-hooks": [
"crate2nix",
"crate2nix_stable"
]
},
"locked": {
"lastModified": 1716549461,
"narHash": "sha256-lHy5kgx6J8uD+16SO47dPrbob98sh+W1tf4ceSqPVK4=",
"owner": "cachix",
"repo": "cachix",
"rev": "e2bb269fb8c0828d5d4d2d7b8d09ea85abcacbd4",
"type": "github"
},
"original": {
"owner": "cachix",
"ref": "latest",
"repo": "cachix",
"type": "github"
}
},
"cachix_3": {
"inputs": {
"devenv": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable"
],
"flake-compat": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable"
],
"nixpkgs": "nixpkgs_3",
"pre-commit-hooks": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable"
]
},
"locked": {
"lastModified": 1716549461,
"narHash": "sha256-lHy5kgx6J8uD+16SO47dPrbob98sh+W1tf4ceSqPVK4=",
"owner": "cachix",
"repo": "cachix",
"rev": "e2bb269fb8c0828d5d4d2d7b8d09ea85abcacbd4",
"type": "github"
},
"original": {
"owner": "cachix",
"ref": "latest",
"repo": "cachix",
"type": "github"
}
},
"crate2nix": {
"inputs": {
"cachix": "cachix",
"crate2nix_stable": "crate2nix_stable",
"devshell": "devshell_3",
"flake-compat": "flake-compat_3",
"flake-parts": "flake-parts_3",
"nix-test-runner": "nix-test-runner_3",
"nixpkgs": [
"tgi-nix",
"nixpkgs"
],
"pre-commit-hooks": "pre-commit-hooks_3"
},
"locked": {
"lastModified": 1723311214,
"narHash": "sha256-xdGZQBEa1AC2us/sY3igS/CucWY6jErXsAvCFRhB2LI=",
"owner": "nix-community",
"repo": "crate2nix",
"rev": "236f6addfd452a48be805819e3216af79e988fd5",
"type": "github"
},
"original": {
"owner": "nix-community",
"repo": "crate2nix",
"type": "github"
}
},
"crate2nix_stable": {
"inputs": {
"cachix": "cachix_2",
"crate2nix_stable": "crate2nix_stable_2",
"devshell": "devshell_2",
"flake-compat": "flake-compat_2",
"flake-parts": "flake-parts_2",
"nix-test-runner": "nix-test-runner_2",
"nixpkgs": "nixpkgs_5",
"pre-commit-hooks": "pre-commit-hooks_2"
},
"locked": {
"lastModified": 1719760004,
"narHash": "sha256-esWhRnt7FhiYq0CcIxw9pvH+ybOQmWBfHYMtleaMhBE=",
"owner": "nix-community",
"repo": "crate2nix",
"rev": "1dee214bb20855fa3e1e7bb98d28922ddaff8c57",
"type": "github"
},
"original": {
"owner": "nix-community",
"ref": "0.14.1",
"repo": "crate2nix",
"type": "github"
}
},
"crate2nix_stable_2": {
"inputs": {
"cachix": "cachix_3",
"crate2nix_stable": "crate2nix_stable_3",
"devshell": "devshell",
"flake-compat": "flake-compat",
"flake-parts": "flake-parts",
"nix-test-runner": "nix-test-runner",
"nixpkgs": "nixpkgs_4",
"pre-commit-hooks": "pre-commit-hooks"
},
"locked": {
"lastModified": 1712821484,
"narHash": "sha256-rGT3CW64cJS9nlnWPFWSc1iEa3dNZecVVuPVGzcsHe8=",
"owner": "nix-community",
"repo": "crate2nix",
"rev": "42883afcad3823fa5811e967fb7bff54bc3c9d6d",
"type": "github"
},
"original": {
"owner": "nix-community",
"ref": "0.14.0",
"repo": "crate2nix",
"type": "github"
}
},
"crate2nix_stable_3": {
"inputs": {
"flake-utils": "flake-utils"
},
"locked": {
"lastModified": 1702842982,
"narHash": "sha256-A9AowkHIjsy1a4LuiPiVP88FMxyCWK41flZEZOUuwQM=",
"owner": "nix-community",
"repo": "crate2nix",
"rev": "75ac2973affa6b9b4f661a7b592cba6e4f51d426",
"type": "github"
},
"original": {
"owner": "nix-community",
"ref": "0.12.0",
"repo": "crate2nix",
"type": "github"
}
},
"devshell": {
"inputs": {
"flake-utils": "flake-utils_2",
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1717408969,
"narHash": "sha256-Q0OEFqe35fZbbRPPRdrjTUUChKVhhWXz3T9ZSKmaoVY=",
"owner": "numtide",
"repo": "devshell",
"rev": "1ebbe68d57457c8cae98145410b164b5477761f4",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "devshell",
"type": "github"
}
},
"devshell_2": {
"inputs": {
"flake-utils": "flake-utils_3",
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1717408969,
"narHash": "sha256-Q0OEFqe35fZbbRPPRdrjTUUChKVhhWXz3T9ZSKmaoVY=",
"owner": "numtide",
"repo": "devshell",
"rev": "1ebbe68d57457c8cae98145410b164b5477761f4",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "devshell",
"type": "github"
}
},
"devshell_3": {
"inputs": {
"flake-utils": "flake-utils_4",
"nixpkgs": [
"crate2nix",
"nixpkgs"
]
},
"locked": {
"lastModified": 1711099426,
"narHash": "sha256-HzpgM/wc3aqpnHJJ2oDqPBkNsqWbW0WfWUO8lKu8nGk=",
"owner": "numtide",
"repo": "devshell",
"rev": "2d45b54ca4a183f2fdcf4b19c895b64fbf620ee8",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "devshell",
"type": "github"
}
},
"flake-compat": {
"locked": {
"lastModified": 1696426674,
"narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
"rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
"revCount": 57,
"type": "tarball",
"url": "https://api.flakehub.com/f/pinned/edolstra/flake-compat/1.0.1/018afb31-abd1-7bff-a5e4-cff7e18efb7a/source.tar.gz"
},
"original": {
"type": "tarball",
"url": "https://flakehub.com/f/edolstra/flake-compat/1.tar.gz"
}
},
"flake-compat_2": {
"locked": {
"lastModified": 1696426674,
"narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
"rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
"revCount": 57,
"type": "tarball",
"url": "https://api.flakehub.com/f/pinned/edolstra/flake-compat/1.0.1/018afb31-abd1-7bff-a5e4-cff7e18efb7a/source.tar.gz"
},
"original": {
"type": "tarball",
"url": "https://flakehub.com/f/edolstra/flake-compat/1.tar.gz"
}
},
"flake-compat_3": {
"locked": {
"lastModified": 1696426674,
"narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
"rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
"revCount": 57,
"type": "tarball",
"url": "https://api.flakehub.com/f/pinned/edolstra/flake-compat/1.0.1/018afb31-abd1-7bff-a5e4-cff7e18efb7a/source.tar.gz"
},
"original": {
"type": "tarball",
"url": "https://flakehub.com/f/edolstra/flake-compat/1.tar.gz"
}
},
"flake-compat_4": {
"locked": {
"lastModified": 1696426674,
"narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
"owner": "edolstra",
"repo": "flake-compat",
"rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
"type": "github"
},
"original": {
"owner": "edolstra",
"repo": "flake-compat",
"type": "github"
}
},
"flake-parts": {
"inputs": {
"nixpkgs-lib": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1719745305,
"narHash": "sha256-xwgjVUpqSviudEkpQnioeez1Uo2wzrsMaJKJClh+Bls=",
"owner": "hercules-ci",
"repo": "flake-parts",
"rev": "c3c5ecc05edc7dafba779c6c1a61cd08ac6583e9",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "flake-parts",
"type": "github"
}
},
"flake-parts_2": {
"inputs": {
"nixpkgs-lib": [
"crate2nix",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1719745305,
"narHash": "sha256-xwgjVUpqSviudEkpQnioeez1Uo2wzrsMaJKJClh+Bls=",
"owner": "hercules-ci",
"repo": "flake-parts",
"rev": "c3c5ecc05edc7dafba779c6c1a61cd08ac6583e9",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "flake-parts",
"type": "github"
}
},
"flake-parts_3": {
"inputs": {
"nixpkgs-lib": [
"crate2nix",
"nixpkgs"
]
},
"locked": {
"lastModified": 1712014858,
"narHash": "sha256-sB4SWl2lX95bExY2gMFG5HIzvva5AVMJd4Igm+GpZNw=",
"owner": "hercules-ci",
"repo": "flake-parts",
"rev": "9126214d0a59633752a136528f5f3b9aa8565b7d",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "flake-parts",
"type": "github"
}
},
"flake-utils": {
"inputs": {
"systems": "systems"
},
"locked": {
"lastModified": 1694529238,
"narHash": "sha256-zsNZZGTGnMOf9YpHKJqMSsa0dXbfmxeoJ7xHlrt+xmY=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "ff7b65b44d01cf9ba6a71320833626af21126384",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_2": {
"inputs": {
"systems": "systems_2"
},
"locked": {
"lastModified": 1701680307,
"narHash": "sha256-kAuep2h5ajznlPMD9rnQyffWG8EM/C73lejGofXvdM8=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "4022d587cbbfd70fe950c1e2083a02621806a725",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_3": {
"inputs": {
"systems": "systems_3"
},
"locked": {
"lastModified": 1701680307,
"narHash": "sha256-kAuep2h5ajznlPMD9rnQyffWG8EM/C73lejGofXvdM8=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "4022d587cbbfd70fe950c1e2083a02621806a725",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_4": {
"inputs": {
"systems": "systems_4"
},
"locked": {
"lastModified": 1701680307,
"narHash": "sha256-kAuep2h5ajznlPMD9rnQyffWG8EM/C73lejGofXvdM8=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "4022d587cbbfd70fe950c1e2083a02621806a725",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_5": {
"inputs": {
"systems": "systems_5"
},
"locked": {
"lastModified": 1710146030,
"narHash": "sha256-SZ5L6eA7HJ/nmkzGG7/ISclqe6oZdOZTNoesiInkXPQ=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "b1d9ab70662946ef0850d488da1c9019f3a9752a",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"flake-utils_6": {
2024-08-12 10:09:16 -06:00
"inputs": {
"systems": "systems_6"
},
"locked": {
"lastModified": 1710146030,
"narHash": "sha256-SZ5L6eA7HJ/nmkzGG7/ISclqe6oZdOZTNoesiInkXPQ=",
"owner": "numtide",
"repo": "flake-utils",
"rev": "b1d9ab70662946ef0850d488da1c9019f3a9752a",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
"gitignore": {
"inputs": {
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"pre-commit-hooks",
"nixpkgs"
]
},
"locked": {
"lastModified": 1709087332,
"narHash": "sha256-HG2cCnktfHsKV0s4XW83gU3F57gaTljL9KNSuG6bnQs=",
"owner": "hercules-ci",
"repo": "gitignore.nix",
"rev": "637db329424fd7e46cf4185293b9cc8c88c95394",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "gitignore.nix",
"type": "github"
}
},
"gitignore_2": {
"inputs": {
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"pre-commit-hooks",
"nixpkgs"
]
},
"locked": {
"lastModified": 1709087332,
"narHash": "sha256-HG2cCnktfHsKV0s4XW83gU3F57gaTljL9KNSuG6bnQs=",
"owner": "hercules-ci",
"repo": "gitignore.nix",
"rev": "637db329424fd7e46cf4185293b9cc8c88c95394",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "gitignore.nix",
"type": "github"
}
},
"gitignore_3": {
"inputs": {
"nixpkgs": [
"crate2nix",
"pre-commit-hooks",
"nixpkgs"
]
},
"locked": {
"lastModified": 1709087332,
"narHash": "sha256-HG2cCnktfHsKV0s4XW83gU3F57gaTljL9KNSuG6bnQs=",
"owner": "hercules-ci",
"repo": "gitignore.nix",
"rev": "637db329424fd7e46cf4185293b9cc8c88c95394",
"type": "github"
},
"original": {
"owner": "hercules-ci",
"repo": "gitignore.nix",
"type": "github"
}
},
"nix-filter": {
"locked": {
"lastModified": 1710156097,
"narHash": "sha256-1Wvk8UP7PXdf8bCCaEoMnOT1qe5/Duqgj+rL8sRQsSM=",
"owner": "numtide",
"repo": "nix-filter",
"rev": "3342559a24e85fc164b295c3444e8a139924675b",
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "nix-filter",
"type": "github"
}
},
"nix-test-runner": {
"flake": false,
"locked": {
"lastModified": 1588761593,
"narHash": "sha256-FKJykltAN/g3eIceJl4SfDnnyuH2jHImhMrXS2KvGIs=",
"owner": "stoeffel",
"repo": "nix-test-runner",
"rev": "c45d45b11ecef3eb9d834c3b6304c05c49b06ca2",
"type": "github"
},
"original": {
"owner": "stoeffel",
"repo": "nix-test-runner",
"type": "github"
}
},
"nix-test-runner_2": {
"flake": false,
"locked": {
"lastModified": 1588761593,
"narHash": "sha256-FKJykltAN/g3eIceJl4SfDnnyuH2jHImhMrXS2KvGIs=",
"owner": "stoeffel",
"repo": "nix-test-runner",
"rev": "c45d45b11ecef3eb9d834c3b6304c05c49b06ca2",
"type": "github"
},
"original": {
"owner": "stoeffel",
"repo": "nix-test-runner",
"type": "github"
}
},
"nix-test-runner_3": {
"flake": false,
"locked": {
"lastModified": 1588761593,
"narHash": "sha256-FKJykltAN/g3eIceJl4SfDnnyuH2jHImhMrXS2KvGIs=",
"owner": "stoeffel",
"repo": "nix-test-runner",
"rev": "c45d45b11ecef3eb9d834c3b6304c05c49b06ca2",
"type": "github"
},
"original": {
"owner": "stoeffel",
"repo": "nix-test-runner",
"type": "github"
}
},
"nixpkgs": {
"locked": {
"lastModified": 1700612854,
"narHash": "sha256-yrQ8osMD+vDLGFX7pcwsY/Qr5PUd6OmDMYJZzZi0+zc=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "19cbff58383a4ae384dea4d1d0c823d72b49d614",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixos-unstable",
"repo": "nixpkgs",
"type": "github"
}
},
"nixpkgs_2": {
"locked": {
"lastModified": 1715534503,
"narHash": "sha256-5ZSVkFadZbFP1THataCaSf0JH2cAH3S29hU9rrxTEqk=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "2057814051972fa1453ddfb0d98badbea9b83c06",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixos-unstable",
"repo": "nixpkgs",
"type": "github"
}
},
"nixpkgs_3": {
"locked": {
"lastModified": 1715534503,
"narHash": "sha256-5ZSVkFadZbFP1THataCaSf0JH2cAH3S29hU9rrxTEqk=",
"owner": "NixOS",
"repo": "nixpkgs",
"rev": "2057814051972fa1453ddfb0d98badbea9b83c06",
"type": "github"
},
"original": {
"owner": "NixOS",
"ref": "nixos-unstable",
"repo": "nixpkgs",
"type": "github"
}
},
"nixpkgs_4": {
"locked": {
"lastModified": 1719506693,
"narHash": "sha256-C8e9S7RzshSdHB7L+v9I51af1gDM5unhJ2xO1ywxNH8=",
"path": "/nix/store/4p0avw1s3vf27hspgqsrqs37gxk4i83i-source",
"rev": "b2852eb9365c6de48ffb0dc2c9562591f652242a",
"type": "path"
},
"original": {
"id": "nixpkgs",
"type": "indirect"
}
},
"nixpkgs_5": {
"locked": {
"lastModified": 1719506693,
"narHash": "sha256-C8e9S7RzshSdHB7L+v9I51af1gDM5unhJ2xO1ywxNH8=",
"path": "/nix/store/4p0avw1s3vf27hspgqsrqs37gxk4i83i-source",
"rev": "b2852eb9365c6de48ffb0dc2c9562591f652242a",
"type": "path"
},
"original": {
"id": "nixpkgs",
"type": "indirect"
}
},
"nixpkgs_6": {
"locked": {
"lastModified": 1723912943,
"narHash": "sha256-39F9GzyhxYcY3wTeKuEFWRJWcrGBosO4nf4xzMTWZX8=",
"owner": "danieldk",
2024-08-12 10:09:16 -06:00
"repo": "nixpkgs",
"rev": "b82cdca86dbb30013b76c4b55d48806476820a5c",
2024-08-12 10:09:16 -06:00
"type": "github"
},
"original": {
"owner": "danieldk",
"ref": "cuda-12.4",
"repo": "nixpkgs",
"type": "github"
}
},
"pre-commit-hooks": {
"inputs": {
"flake-compat": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"flake-compat"
],
"gitignore": "gitignore",
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"nixpkgs"
],
"nixpkgs-stable": [
"crate2nix",
"crate2nix_stable",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1719259945,
"narHash": "sha256-F1h+XIsGKT9TkGO3omxDLEb/9jOOsI6NnzsXFsZhry4=",
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"rev": "0ff4381bbb8f7a52ca4a851660fc7a437a4c6e07",
"type": "github"
},
"original": {
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"type": "github"
}
},
"pre-commit-hooks_2": {
"inputs": {
"flake-compat": [
"crate2nix",
"crate2nix_stable",
"flake-compat"
],
"gitignore": "gitignore_2",
"nixpkgs": [
"crate2nix",
"crate2nix_stable",
"nixpkgs"
],
"nixpkgs-stable": [
"crate2nix",
"crate2nix_stable",
"nixpkgs"
]
},
"locked": {
"lastModified": 1719259945,
"narHash": "sha256-F1h+XIsGKT9TkGO3omxDLEb/9jOOsI6NnzsXFsZhry4=",
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"rev": "0ff4381bbb8f7a52ca4a851660fc7a437a4c6e07",
"type": "github"
},
"original": {
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"type": "github"
}
},
"pre-commit-hooks_3": {
"inputs": {
"flake-compat": [
"crate2nix",
"flake-compat"
],
"flake-utils": "flake-utils_5",
"gitignore": "gitignore_3",
"nixpkgs": [
"crate2nix",
"nixpkgs"
],
"nixpkgs-stable": [
"crate2nix",
"nixpkgs"
]
},
"locked": {
"lastModified": 1712055707,
"narHash": "sha256-4XLvuSIDZJGS17xEwSrNuJLL7UjDYKGJSbK1WWX2AK8=",
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"rev": "e35aed5fda3cc79f88ed7f1795021e559582093a",
"type": "github"
},
"original": {
"owner": "cachix",
"repo": "pre-commit-hooks.nix",
"type": "github"
}
},
"root": {
"inputs": {
"crate2nix": "crate2nix",
"flake-utils": "flake-utils_6",
"nix-filter": "nix-filter",
"nixpkgs": [
"tgi-nix",
"nixpkgs"
],
2024-08-09 07:24:21 -06:00
"rust-overlay": "rust-overlay",
"tgi-nix": "tgi-nix"
}
},
2024-08-09 07:24:21 -06:00
"rust-overlay": {
"inputs": {
"nixpkgs": [
"tgi-nix",
"nixpkgs"
]
},
"locked": {
Lots of improvements (Still 2 allocators) (#2449) * Making prefix/flashinfer the default and testing the full release tests. * Include flashinfer in the docker. * Using prebuilt. * Allowing window_left_size (dummy version). * Disabling flashinfer/prefix caching on odd head_dim * Disable prefix caching for lora. * More specific codes. * Update lock * Updating integration tests with new values with FI/FD. Remove paged as a default too, and using FD everywhere. * Update cargo lock ? * Upgrade to 1.80 because of bitstream... * Everywhere 1.80 * Forgot last default place. * Apply suggestions from code review Co-authored-by: drbh <david.richard.holtz@gmail.com> * Updated flake lock * Tmp * Upgrade resolution system for less errors in resolution. * Remove lambda for cleaner function. * Handling debugger. * OVerride the env in server tests. * Is this enough to make it work ? * This seems to be working. * Downgrade some logs. * Fixing the default for vlm. * Don't enable prefix caching on VLM just yet. * Change `add_special_tokens` in order to have the correct tokens for chat input and not (since it's super important with the prefixing now) * Fixing prefix caching for flashdecoding. * Update all models. * Fixed flashinfer version. * add_special_tokens is internal only * Fixing seqlen with the new vlms. * Fixing the issue with `add_special_tokens` not being passed around. * Fixing the test. * Removing encoder_decoder (seq2seq). * Update the chat test. * Fixing the batching tokenization in flash causal lm. * Truncating left for radix purposes. * Oops this doesn't belong here. * Put back default pure shell. * Update server tests - Default to throughput test in k6 - Use TGI_WIGGLE_ROOM to adjust wiggle room * Only n_heads / process_group.size() are necessary. * Revert the integrationt tests change (seem linked to head_size modification). * Adding error message when assert is violated. * Fixing the free algorithm to handle times where the common prefix is smaller. * Apply suggestions from code review Co-authored-by: OlivierDehaene <olivier@huggingface.co> * Update server/text_generation_server/layers/attention/common.py Co-authored-by: OlivierDehaene <olivier@huggingface.co> * Fix disabling prefix caching - Fix windowing checks. * Revert the Cohere tokenizer change (for now using a revision instead). * Fmt. --------- Co-authored-by: drbh <david.richard.holtz@gmail.com> Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2024-08-29 08:29:01 -06:00
"lastModified": 1724638882,
"narHash": "sha256-ap2jIQi/FuUHR6HCht6ASWhoz8EiB99XmI8Esot38VE=",
2024-08-09 07:24:21 -06:00
"owner": "oxalica",
"repo": "rust-overlay",
Lots of improvements (Still 2 allocators) (#2449) * Making prefix/flashinfer the default and testing the full release tests. * Include flashinfer in the docker. * Using prebuilt. * Allowing window_left_size (dummy version). * Disabling flashinfer/prefix caching on odd head_dim * Disable prefix caching for lora. * More specific codes. * Update lock * Updating integration tests with new values with FI/FD. Remove paged as a default too, and using FD everywhere. * Update cargo lock ? * Upgrade to 1.80 because of bitstream... * Everywhere 1.80 * Forgot last default place. * Apply suggestions from code review Co-authored-by: drbh <david.richard.holtz@gmail.com> * Updated flake lock * Tmp * Upgrade resolution system for less errors in resolution. * Remove lambda for cleaner function. * Handling debugger. * OVerride the env in server tests. * Is this enough to make it work ? * This seems to be working. * Downgrade some logs. * Fixing the default for vlm. * Don't enable prefix caching on VLM just yet. * Change `add_special_tokens` in order to have the correct tokens for chat input and not (since it's super important with the prefixing now) * Fixing prefix caching for flashdecoding. * Update all models. * Fixed flashinfer version. * add_special_tokens is internal only * Fixing seqlen with the new vlms. * Fixing the issue with `add_special_tokens` not being passed around. * Fixing the test. * Removing encoder_decoder (seq2seq). * Update the chat test. * Fixing the batching tokenization in flash causal lm. * Truncating left for radix purposes. * Oops this doesn't belong here. * Put back default pure shell. * Update server tests - Default to throughput test in k6 - Use TGI_WIGGLE_ROOM to adjust wiggle room * Only n_heads / process_group.size() are necessary. * Revert the integrationt tests change (seem linked to head_size modification). * Adding error message when assert is violated. * Fixing the free algorithm to handle times where the common prefix is smaller. * Apply suggestions from code review Co-authored-by: OlivierDehaene <olivier@huggingface.co> * Update server/text_generation_server/layers/attention/common.py Co-authored-by: OlivierDehaene <olivier@huggingface.co> * Fix disabling prefix caching - Fix windowing checks. * Revert the Cohere tokenizer change (for now using a revision instead). * Fmt. --------- Co-authored-by: drbh <david.richard.holtz@gmail.com> Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2024-08-29 08:29:01 -06:00
"rev": "19b70f147b9c67a759e35824b241f1ed92e46694",
2024-08-09 07:24:21 -06:00
"type": "github"
},
"original": {
"owner": "oxalica",
"repo": "rust-overlay",
"type": "github"
}
},
"systems": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
2024-08-12 10:09:16 -06:00
"systems_2": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"systems_3": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"systems_4": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"systems_5": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"systems_6": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
"tgi-nix": {
"inputs": {
"flake-compat": "flake-compat_4",
"nixpkgs": "nixpkgs_6"
},
"locked": {
"lastModified": 1724784743,
"narHash": "sha256-NdEoWeNwR/ZstYnHaiQWIYZvr7VsrAh7g3+ZHUPrxuI=",
"owner": "danieldk",
"repo": "tgi-nix",
"rev": "c9580c3e39a855246bb87b584bbea1885b44f524",
"type": "github"
},
"original": {
"owner": "danieldk",
"repo": "tgi-nix",
"type": "github"
}
}
},
"root": "root",
"version": 7
}