Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/flake.lock

998 lines
26 KiB
Plaintext
Raw Permalink Normal View History

Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
{
"nodes": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"flake-compat": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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": {
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"locked": {
"lastModified": 1696426674,
"narHash": "sha256-kvjfFW7WAETZlt09AgDn1MrtKzP7t90Vf7vypd3OL1U=",
"owner": "edolstra",
"repo": "flake-compat",
"rev": "0f9255e01c2351cc7d116c072cb317785dd33b33",
"type": "github"
},
"original": {
"owner": "edolstra",
"repo": "flake-compat",
"type": "github"
}
},
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"flake-utils": {
"inputs": {
"systems": "systems"
},
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"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"
}
},
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"flake-utils_6": {
Updating the flake. (#2404)
2024-08-12 10:09:16 -06:00
"inputs": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"systems": "systems_6"
},
"locked": {
Stream options. (#2533) * Stream options. * Fetch stuff from nix integration test for easier testing. * Adding the assert. * Only send the usage when asked for. * Update the docs. * Impure test because we need network. * develop. * Optional usage. * Fixes. * Workflow
2024-09-19 12:50:37 -06:00
"lastModified": 1726560853,
"narHash": "sha256-X6rJYSESBVr3hBoH0WbKE5KvhPU5bloyZ2L4K60/fPQ=",
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"owner": "numtide",
"repo": "flake-utils",
Stream options. (#2533) * Stream options. * Fetch stuff from nix integration test for easier testing. * Adding the assert. * Only send the usage when asked for. * Update the docs. * Impure test because we need network. * develop. * Optional usage. * Fixes. * Workflow
2024-09-19 12:50:37 -06:00
"rev": "c1dfcf08411b08f6b8615f7d8971a2bfa81d5e8a",
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"flake-utils_7": {
"inputs": {
"systems": "systems_7"
},
"locked": {
Mllama flash version (#2585) * Working loading state. * Preprocessing. * Working state ? (Broke idefics1 temporarily). * Cleaner condition. * Fix idefics. * Updating config, removing TODO * Mllama * Ugrade transformers 4.45 * Flashing mllama. * Starting to get there. * Working state. * Integrations tests for mllama (cutting to 10 tokens because there seems' to be instability after (meaning size of the batch matters. * Updating model link. * Earlier assert. * Fix vlm ? * remove log. * Force ignore all images but last. * Default dtype bfloat16. * Update integration test after switch to bf16. * Remove dead code. * Removed dead code. * Upgrade the flake to latest transformers/tokenizers * Move to hf tgi-nix * Upgrade to 0.5.0
2024-10-02 03:22:13 -06:00
"lastModified": 1726560853,
"narHash": "sha256-X6rJYSESBVr3hBoH0WbKE5KvhPU5bloyZ2L4K60/fPQ=",
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"owner": "numtide",
"repo": "flake-utils",
Mllama flash version (#2585) * Working loading state. * Preprocessing. * Working state ? (Broke idefics1 temporarily). * Cleaner condition. * Fix idefics. * Updating config, removing TODO * Mllama * Ugrade transformers 4.45 * Flashing mllama. * Starting to get there. * Working state. * Integrations tests for mllama (cutting to 10 tokens because there seems' to be instability after (meaning size of the batch matters. * Updating model link. * Earlier assert. * Fix vlm ? * remove log. * Force ignore all images but last. * Default dtype bfloat16. * Update integration test after switch to bf16. * Remove dead code. * Removed dead code. * Upgrade the flake to latest transformers/tokenizers * Move to hf tgi-nix * Upgrade to 0.5.0
2024-10-02 03:22:13 -06:00
"rev": "c1dfcf08411b08f6b8615f7d8971a2bfa81d5e8a",
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"type": "github"
},
"original": {
"owner": "numtide",
"repo": "flake-utils",
"type": "github"
}
},
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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: try to reduce the number of Rust rebuilds (#2424) Try to reduce the number of router/launcher rebuilds by filtering sources. In this way, recompiles should only be triggered by changes in Cargo or Rust files.
2024-08-16 02:01:01 -06:00
"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: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"nixpkgs": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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": {
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"locked": {
nix: update nixpkgs (#2746) Updates from Triton 2.1.0 to 3.1.0 (among other things).
2024-11-14 10:48:20 -07:00
"lastModified": 1731562571,
"narHash": "sha256-9V0C/H6NL2Vk3Y76msqNA8TgwZ6Ge4frOVawTNFJQmM=",
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"owner": "nixos",
Updating the flake. (#2404)
2024-08-12 10:09:16 -06:00
"repo": "nixpkgs",
nix: update nixpkgs (#2746) Updates from Triton 2.1.0 to 3.1.0 (among other things).
2024-11-14 10:48:20 -07:00
"rev": "19d66fab291f90ce56d0479b128cc7a5271bf666",
Updating the flake. (#2404)
2024-08-12 10:09:16 -06:00
"type": "github"
},
"original": {
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"owner": "nixos",
"ref": "nixos-unstable-small",
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"repo": "nixpkgs",
"type": "github"
}
},
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"root": {
"inputs": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"crate2nix": "crate2nix",
"flake-utils": "flake-utils_6",
nix: try to reduce the number of Rust rebuilds (#2424) Try to reduce the number of router/launcher rebuilds by filtering sources. In this way, recompiles should only be triggered by changes in Cargo or Rust files.
2024-08-16 02:01:01 -06:00
"nix-filter": "nix-filter",
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"nixpkgs": [
"tgi-nix",
"nixpkgs"
],
flake: use rust-overlay (#2390)
2024-08-09 07:24:21 -06:00
"rust-overlay": "rust-overlay",
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"tgi-nix": "tgi-nix"
}
},
flake: use rust-overlay (#2390)
2024-08-09 07:24:21 -06:00
"rust-overlay": {
"inputs": {
"nixpkgs": [
"tgi-nix",
"nixpkgs"
]
},
"locked": {
We can have a tokenizer anywhere. (#2527) * We can have a tokenizer anywhere. * Handling potential lack of offsets (python tokenizer) * Remove redundancy. * Fixing the tests. * Flake.lock update ? * Fixing the GIL locking. * Fixing mamba by using the transformers version. * Adding the legacy handle. * Ellide lifetime. * Lint. * Deprecation message. * Fixing bad rebase.
2024-10-27 22:00:24 -06:00
"lastModified": 1729045942,
"narHash": "sha256-HjmK0x5Zm2TK2vFpC7XBM2e3EDNVnAIuEoU2FkeN8xw=",
flake: use rust-overlay (#2390)
2024-08-09 07:24:21 -06:00
"owner": "oxalica",
"repo": "rust-overlay",
We can have a tokenizer anywhere. (#2527) * We can have a tokenizer anywhere. * Handling potential lack of offsets (python tokenizer) * Remove redundancy. * Fixing the tests. * Flake.lock update ? * Fixing the GIL locking. * Fixing mamba by using the transformers version. * Adding the legacy handle. * Ellide lifetime. * Lint. * Deprecation message. * Fixing bad rebase.
2024-10-27 22:00:24 -06:00
"rev": "9de3cea452d2401d6f93c06ad985178a4e11d1fc",
flake: use rust-overlay (#2390)
2024-08-09 07:24:21 -06:00
"type": "github"
},
"original": {
"owner": "oxalica",
"repo": "rust-overlay",
"type": "github"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"systems": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
Updating the flake. (#2404)
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": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"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"
}
},
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"systems_7": {
"locked": {
"lastModified": 1681028828,
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
"owner": "nix-systems",
"repo": "default",
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
"type": "github"
},
"original": {
"owner": "nix-systems",
"repo": "default",
"type": "github"
}
},
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"tgi-nix": {
"inputs": {
nix: incremental build of the launcher (#2410)
2024-08-13 02:44:15 -06:00
"flake-compat": "flake-compat_4",
Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) * Adding prefix test. * [WIP] tmp dump of integration load tests. * Remove other tensor creation. * Fixed the radix tree. Used a slice everywhere in radix.rs to keep the cheap Arc cloning instead of recomputing the input_ids. * Fix parsing * Is it really flashinfer version ? * Remove some comments. * Revert the max prefix hit. * Adding numpy to diff. * Upgraded flashinfer. * Upgrading some stuff. * Are we done yet ? * Minor fixup * Remove 1 log and put back the other. * Add comment for why slot 0 is OK. * Mounting on the job. * Get me a debug branch * Debugging CIs is fun. * Attempt #28 * wip * Tmate. * Praying. * Updating VLM causal model with updated context. * Important line got squashed. * Tmate again. * Fingers crossed. * We want only 1 run of integration tests..... --------- Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>
2024-09-11 10:10:40 -06:00
"flake-utils": "flake-utils_7",
nix: update to CUDA 12.4 (#2429) * Update to CUDA 12.4 * poetry2nix: follow tgi-nix nixpkgs
2024-08-19 01:28:38 -06:00
"nixpkgs": "nixpkgs_6"
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
},
"locked": {
Remove vLLM dependency for CUDA (#2751) * Remove vLLM dependency for CUDA This change adds `attention-kernels` as a dependency for paged attention and cache reshaping. With that, we don't use vLLM anywhere for CUDA. Tested run (since we don't have paged attention in CI): ``` ❯ ATTENTION=paged python -m pytest integration-tests -k "llama and awq" --release [...] 5 snapshots passed. ``` * Fix clippy warning
2024-11-17 09:34:50 -07:00
"lastModified": 1731674227,
"narHash": "sha256-k/ur37KSc+RXcwwz0tgxeamz6wQ5rsOe5hMepzIdD2s=",
Mllama flash version (#2585) * Working loading state. * Preprocessing. * Working state ? (Broke idefics1 temporarily). * Cleaner condition. * Fix idefics. * Updating config, removing TODO * Mllama * Ugrade transformers 4.45 * Flashing mllama. * Starting to get there. * Working state. * Integrations tests for mllama (cutting to 10 tokens because there seems' to be instability after (meaning size of the batch matters. * Updating model link. * Earlier assert. * Fix vlm ? * remove log. * Force ignore all images but last. * Default dtype bfloat16. * Update integration test after switch to bf16. * Remove dead code. * Removed dead code. * Upgrade the flake to latest transformers/tokenizers * Move to hf tgi-nix * Upgrade to 0.5.0
2024-10-02 03:22:13 -06:00
"owner": "huggingface",
"repo": "text-generation-inference-nix",
Remove vLLM dependency for CUDA (#2751) * Remove vLLM dependency for CUDA This change adds `attention-kernels` as a dependency for paged attention and cache reshaping. With that, we don't use vLLM anywhere for CUDA. Tested run (since we don't have paged attention in CI): ``` ❯ ATTENTION=paged python -m pytest integration-tests -k "llama and awq" --release [...] 5 snapshots passed. ``` * Fix clippy warning
2024-11-17 09:34:50 -07:00
"rev": "407b9e22a0b7121bf6e171d67ce0144e3f3e39bf",
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"type": "github"
},
"original": {
Mllama flash version (#2585) * Working loading state. * Preprocessing. * Working state ? (Broke idefics1 temporarily). * Cleaner condition. * Fix idefics. * Updating config, removing TODO * Mllama * Ugrade transformers 4.45 * Flashing mllama. * Starting to get there. * Working state. * Integrations tests for mllama (cutting to 10 tokens because there seems' to be instability after (meaning size of the batch matters. * Updating model link. * Earlier assert. * Fix vlm ? * remove log. * Force ignore all images but last. * Default dtype bfloat16. * Update integration test after switch to bf16. * Remove dead code. * Removed dead code. * Upgrade the flake to latest transformers/tokenizers * Move to hf tgi-nix * Upgrade to 0.5.0
2024-10-02 03:22:13 -06:00
"owner": "huggingface",
"repo": "text-generation-inference-nix",
Add experimental flake (#2384) Add flake.nix
2024-08-09 04:32:37 -06:00
"type": "github"
}
}
},
"root": "root",
"version": 7
}