Assisted-by: Codex Signed-off-by: yangzhuxinyzx <153831768+yangzhuxinyzx@users.noreply.github.com>
104 lines
14 KiB
JSON
104 lines
14 KiB
JSON
{
|
|
"llama_cpp_commit": "002a12ad25503a93501b2e188c360029830a241a",
|
|
"plugin_commit": "aa09d6522f29325d64d999d7d7c794f79836de07",
|
|
"files": {
|
|
"csrc/quantization/gguf_upstream/llama.cpp/LICENSE": "94f29bbed6a22c35b992c5c6ebf0e7c92f13b836b90f36f461c9cf2f0f1d010d",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/include/ggml-alloc.h": "94e4cd069b9313b2ceb35dacec901981e0bb478d8bb31035b7126be091998c23",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/include/gguf.h": "e56714aab702e5ce62ee587a409643c08f7e93e8fbb77f48ef7cc85075f96fa4",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/include/ggml-backend.h": "46d84cb998105f871240864fd0f55446939a2fe86c5c281afa63a010fb1f65a2",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/include/ggml-cuda.h": "9cbfcea49f6da4d07f41dc22fa8dbf870825faaa2a68e34e65fe30ea6c41e042",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/include/ggml.h": "9ac7ee3d3a957e5f7b21b104d3e3dc50b1b106f808f9d6735ead950450bfeec6",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-common.h": "0061131b615c5721fc88a78feeb22c1f8c450f1c2646a317d80796a653bf595c",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-impl.h": "43564db0238aebb7ed68501e346c194866b5dac218d1d37b26baff9f458c00d3",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq.cuh": "50db23f5055af6e28c142fcb4c7fb16c51f7137184ebf8c0ca113ed88906851b",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-rdna2.cuh": "758be2a33b89018841f432c15cd63009ad212d71eae888a04b4535cb64941aa7",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmid.cu": "cd5a6895c52a413f7c8f7273d02ed5a1253d3b6833701fa40b68e3716bbc3c87",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/dequantize.cuh": "135b3f11b7e7e49d96b18cc653a0440e79e05591397a3d12f94ce61b58432469",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmid.cuh": "236962648e49c0faa2d76f505c781e36a99c833b27ff3a871111d9de135803ed",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmvq.cu": "d4c70f68ab79d463fd6fd52cac66a62e915858397ba4b2b7f658a7fbf13121f3",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-pascal-older.cuh": "48bae44f1f0e667fa02fb898859eb18c03961bdbadf53c1e22d98801ed70affe",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mma.cuh": "c7e0f3332da182e203b4b953f9fa8535ffca3767d2b7d4d7dbf7ce486262d1af",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-pascal-dp4a.cuh": "67a93b6d26d3e16e77fd285dd77e7cca7848fb0b0d68897c2ff1e8cc47102263",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-vec-dot.cuh": "58e87f162ec6e4bd5d23e99aeac76f3dd0e13a6cdfe01165cae806b51fe9ae65",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-rdna4.cuh": "e40c9c5fe85607db07ae351dd6ca13c92caaa238e2a62d5134877d9fbcb5c645",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-ampere.cuh": "6de9336a6c2f65c0ad83cbe9303dcd03e8cbb6185d15346133a31421000f6408",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmf.cuh": "ec4fa21930d65f59bd77ee2fdfdbbc9bc1690b12071e3885ba10d5ac2c73234e",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-blackwell.cuh": "8bec1e65a3a2a58fab1f406225f6ba2f1a4c38a19793dfa255baff69bc044d70",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmvq.cuh": "b37f8359f519ba90ddecd9cb3ca5f8c2ae05685bfae6813d435d75763c2bb006",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-rdna3.cuh": "a1ac4f4fa799f2fb200ead23f3403bb0f729d41109b8967c6d76216768aae0cf",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmvf.cuh": "bca80856e91767311caf4c8bf62309efe246ff907e167f45aabc2a9eaba00716",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-load-tiles.cuh": "f1adb201fa40087e294c40887e62f583f6a7adf40ddca542a735774742e0ae2c",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/quantize.cuh": "112e190a096e1fa68d4c72ca2a450cb202586e3f2919c884f3e3316a8d5c57cd",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-gcn.cuh": "f669a723fc19d1e650de33a2852a10472a5773b0c8a3cd5b96662bc4fe6ebfe3",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/convert.cuh": "fc32372473421c99494d7eea21ab510a8cea61d637f572afe34ed9db32b0d6ce",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/convert.cu": "8ebad5e72905e1218c93e3c636c8317896ba385b07d0c41a35a432ca88654c1c",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq.cu": "8acdffe7ccf49698083dfc3e32ae3ef015fb99d6a790adc860344aed401fee08",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/quantize.cu": "71cd7baab62ee1f457d23ae648c381d18b9b1327ec34832f31463b14b81895b3",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmf.cu": "08bfea71b2f25d273b82f53bbb2181c60b3e9bb22641d3c4ed93067ce4bb3de1",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmvf.cu": "0aca92c9d54cf4a17cf79ee082f243b99c9bf62915e523050ab57c55e30555a1",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/unary.cuh": "a6903bb02577a33b79c738e62e425867f9122d1b4981a3b228062b4f978b2858",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-cdna.cuh": "314eeb8453834723d5224012f692f70673f86ecc42d2b6d6f2005a0fad124dbc",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/common.cuh": "de910de24b186d60216791828a52ec56dd0126fdf29eed6a4e0536104fd65520",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/mmq-config-rdna3-5.cuh": "5243cb07aded29b0bd3254cf9f9856989f53b133a73874388282a35c3990f0cd",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/vecdotq.cuh": "a7fd4281ad9f0a6d9373c776325411d2522e0b62ffae2c16e91e667a1af251fe",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/vendors/musa.h": "4874631c16eebbfc6d0f3081779dbe00890b7f94561db7224e4a517f33eb5a3e",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h": "e7847065d5d741f892d2f1f7aaaa8f418a41e3b983d1e6f09010055d4d1c38d1",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/vendors/hip.h": "c22d5824001743b371f6f158179b123aaa3df6ed8b572af6df711b3861a49e05",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu": "c4f568105a3ff273287b04c58879ea455efd5fa05aa72da9ef0efeb7ab9de520",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_11.cu": "56ad9283c689b9873371ee3feb5d72d862f272e22bf21a1ff582f3556c69ac79",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu": "8167508364494a8f51f736186c5294585a26302cb034e051b8b80acf1db18850",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_2.cu": "c6093a25b6b64837d84e8550c2e6a78b8c4737332aa40e8be6ceb2bb04eb233f",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu": "b38f4de9a3563debaf4796d6772e1ed72ce6944c2b8b03f9c26bf19191addee7",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu": "989943d6501a74927d079eacca793e94a1233863196c94dd20e459017ed76fc2",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_9.cu": "2e950c4704407339bbe3047c2028accdc503e428fc88bc82238b0270237459c2",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu": "549d0c56b4b7ffccf262a611e28d257ce8e7ee94ce7ac814259c427eaeb10fe8",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu": "a1312dd1316cd75b4a18e2c4a4c34d54ddfcd92b7fc1e45d4daee101e8d69f00",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu": "a03418c7c0607a3ce3707129dd7e0fcd18d36f241c55289a274fac66f1548f93",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu": "2ab47361d40a9ece25406c20693424a466c93bcb5cdb5c06cee8f9d03a806beb",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu": "8a8c0da33c1c44fcbe516c6c7bd7bf1a6f3b934b63eaf99333e3fba42bfebbea",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_15.cu": "ce65eb4614112d7cdbf7634aeb35200e1c4ec953c862ea0239c61035d2e0e2fb",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu": "e378922ee4aaabe395e7e3f620a38ae26e36e27b46036b8b7fea71292bf8cc2b",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_10.cu": "1f7692c8454683d97951ab3b56c3404089bc6e7ac9fd8e42fd89e069165841cd",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu": "b0f6646afd4a8cc45aaf390a004700057baeae6d87d672dcd67c21a0a81eb74f",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-nvfp4.cu": "b88918c580b960ba3b22cd2228a85849cb244a8027f699ad3f50027ecfb74759",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_16.cu": "af9a987d95b380cba2cf24eb137ccd371e42038535357a83a9dc179274a334b6",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_5.cu": "d35d85ef1eed82154f90b6196cb51d2e1df82bef04a7e01634e8e064e0e6cec4",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_3.cu": "840ae67f3bb493d2e66f2882db271645f5a9f10874650d43c132e43f5eaab557",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu": "3e54437db9b0cdda4ddb629982f1f083458de06771a04e5d25ab3e65dbca9e95",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu": "c98bbe1dd91e03362f4136357c6f4e4e2c5328902fdc6fd857d0f608386ffb2e",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_14.cu": "9392a013e2409e6e8951231486a665167a008dfeb2a482c27c68391cb9f3563f",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_1.cu": "48fddfa154dd4942e943a47a697597e3d2e5406f4d7fae74687bf12e23aeefb0",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q1_0.cu": "bca0611976cc447dc317e3fa81954f69061e45a9370b24fcbdddd9b5340b7da6",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu": "34a443ed0e68b1ad614eb251758d0f43f003ce8d10e7833f9f58a46677d336db",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_4.cu": "f09068f887bba46756ce3de2b1051b4b6d26e0fbf97c89fbc666d1b63855028c",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_8.cu": "50f55a27ffbf909727ddd2f97658602d118e8e87d66035f72c315676ef7c1943",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_0.cu": "41253e37b9d032e78135d8bcee4544de82e07002530f7045eccf782727c8a784",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-mxfp4.cu": "c9be52057f9662aaa0479e5948d6dffed2de2a344dec6c90f1ed3d9d32b42497",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu": "7fa1a4a0aaec59e2e27eb40a13078be685952e446c5c9fb0840a47d0e28a17bf",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu": "8a841418b1b818a13f739759ea0d36ed778e1b6343aee85fdc58d341b169bd55",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_13.cu": "cc1aef2d65fdccfaf650c019d38a32831027faaca28a10fe45d43a16317b6f0a",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu": "13af5ff17c13dbbe712a6f400b83b69da77792969162c6f345491392d36c1d51",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_6.cu": "7fc80d943ea461f79641bf8c65a6b846ed1a4e7025ec0f8bd97c1cf45ab3503e",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_7.cu": "30c54b581a145dce88bf0c78ce262fe32028fc505dabc0d43133751ebc8cbbb5",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu": "3847ca2cefb02dd316033e05db5451b24440cf6ab4cb2d23b4f54a388b492edc",
|
|
"csrc/quantization/gguf_upstream/llama.cpp/ggml/src/ggml-cuda/template-instances/mmf-instance-ncols_12.cu": "2000decac72b0078ec5a510a23d710a59c1ea6dab8a342b87ae033d3a11130f0"
|
|
},
|
|
"adapter_original_sha256": {
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/runtime_dequant_blas.cu": "fcaadbedeab798e7a59ff975356825da376ca5e72aaebcdba91bd343a7102283",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/runtime_dense.cu": "d8163a0cea18a0941ff8f42912e2153cdbe89a6bd5cd76eedf91d8ea6c24bccc",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/LICENSE.plugin": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/ggml_constants.cuh": "295db0a065da6fbd055192bdd236bb7987c18f6e0a49c9d8d1c0270060a7e658",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/runtime.cu": "ba82e2157a6a000cab9edbbd093055ea0d4a2df3006067f9a88c09f6bbb7cc82",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/runtime_moe.cu": "1886208138901d1ed25fd8cd691f1a3e97339ba91f54d9a034329c82387375ca",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/torch_context.cuh": "d39f74b1538ea22632d77aa120ee6a5cd331e3ea00edefc9564cabbdaf5ad838",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/ggml_dypes.cuh": "50c5e020fa3571b8268138d96f951ee9569b5f5c727c27487f084fa51f743668",
|
|
"csrc/libtorch_stable/quantization/gguf_upstream/torch_context.cu": "694663527d4f2c405e96e25bd90dc26e51687560ddc2f66f91e7c684bca89fbd"
|
|
},
|
|
"adapter_changes": [
|
|
"Native-only bindings in separate vllm._C_gguf extension",
|
|
"TQ1_0/TQ2_0 CUDA dequantization and operation-specific MMVQ admission",
|
|
"KernelConfig governs compute policy; no GGML_CUDA_CUBLAS_COMPUTE_TYPE switch",
|
|
"Explicit FP32 inputs retain FP32 BLAS arithmetic"
|
|
]
|
|
}
|