diff --git a/flake.lock b/flake.lock index d64b76b1..2e7ddb29 100644 --- a/flake.lock +++ b/flake.lock @@ -978,15 +978,16 @@ "nixpkgs": "nixpkgs_6" }, "locked": { - "lastModified": 1738251792, - "narHash": "sha256-pHwXzy/TmIAKi1d9qs5USwxDtYf4DucGK9mhGmXxUfQ=", + "lastModified": 1738315729, + "narHash": "sha256-tizNB3LbhPWgqs/PGgFdTxudqkttqo+R0NBkaaQP3ak=", "owner": "huggingface", "repo": "text-generation-inference-nix", - "rev": "c7f53c9ba51f7d1502a0f1c64bf81aad57f2a097", + "rev": "a3872305034ead72328e84628974d66969b46074", "type": "github" }, "original": { "owner": "huggingface", + "ref": "moe_0.8.2", "repo": "text-generation-inference-nix", "type": "github" } diff --git a/flake.nix b/flake.nix index 83cedfa6..28555424 100644 --- a/flake.nix +++ b/flake.nix @@ -5,7 +5,7 @@ inputs.nixpkgs.follows = "tgi-nix/nixpkgs"; }; nix-filter.url = "github:numtide/nix-filter"; - tgi-nix.url = "github:huggingface/text-generation-inference-nix"; + tgi-nix.url = "github:huggingface/text-generation-inference-nix/moe_0.8.2"; nixpkgs.follows = "tgi-nix/nixpkgs"; flake-utils.url = "github:numtide/flake-utils"; rust-overlay = { diff --git a/server/pyproject.toml b/server/pyproject.toml index 8888f5c6..da3ba820 100644 --- a/server/pyproject.toml +++ b/server/pyproject.toml @@ -75,7 +75,7 @@ marlin-kernels = [ { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp311-cp311-linux_x86_64.whl", marker = "python_version == '3.11'" }, { url = "https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl", marker = "python_version == '3.12'" }, ] -moe-kernels.url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.1/moe_kernels-0.8.1+cu123torch2.5-cp39-abi3-linux_x86_64.whl" +moe-kernels.url = "https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl" [tool.pytest.ini_options] markers = ["private: marks tests as requiring an admin hf token (deselect with '-m \"not private\"')"]