updated with vllm based values

rh-pre-commit.version: 2.3.2
rh-pre-commit.check-secrets: ENABLED
This commit is contained in:
Antony Sallas 2025-10-22 18:20:32 +08:00
parent a701f68bd7
commit 17e74251e2
11 changed files with 551 additions and 102 deletions

View file

@ -41,7 +41,7 @@ def available_providers() -> list[ProviderSpec]:
provider_type="inline::sentence-transformers",
# CrossEncoder depends on torchao.quantization
pip_packages=[
"torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu",
"torch torchvision torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cu130",
"sentence-transformers --no-deps",
# required by some SentenceTransformers architectures for tensor rearrange/merge ops
"einops",

View file

@ -32,7 +32,7 @@ def available_providers() -> list[ProviderSpec]:
"provider_type": "inline::torchtune-cpu",
"pip_packages": (
cast(list[str], torchtune_def["pip_packages"])
+ ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cpu"]
+ ["torch torchtune>=0.5.0 torchao>=0.12.0 --extra-index-url https://download.pytorch.org/whl/cu130"]
),
},
),

View file

@ -98,7 +98,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
params = params.model_copy()
# Apply vLLM-specific defaults
if params.max_tokens is None and self.config.max_tokens:
if (params.max_tokens is None or params.max_tokens == 0) and self.config.max_tokens:
params.max_tokens = self.config.max_tokens
# This is to be consistent with OpenAI API and support vLLM <= v0.6.3

View file

@ -141,6 +141,7 @@
"integrity": "sha512-IaaGWsQqfsQWVLqMn9OB92MNN7zukfVA4s7KKAI0KfrrDsZ0yhi5uV4baBuLuN7n3vsZpwP8asPPcVwApxvjBQ==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@ampproject/remapping": "^2.2.0",
"@babel/code-frame": "^7.27.1",
@ -760,6 +761,7 @@
}
],
"license": "MIT",
"peer": true,
"engines": {
"node": ">=18"
},
@ -783,6 +785,7 @@
}
],
"license": "MIT",
"peer": true,
"engines": {
"node": ">=18"
}
@ -3964,6 +3967,7 @@
"resolved": "https://registry.npmjs.org/@types/node/-/node-24.3.0.tgz",
"integrity": "sha512-aPTXCrfwnDLj4VvXrm+UUCQjNEvJgNA8s5F1cvwQU+3KNltTOkBm1j30uNLyqqPNe7gE3KFzImYoZEfLhp4Yow==",
"license": "MIT",
"peer": true,
"dependencies": {
"undici-types": "~7.10.0"
}
@ -3983,6 +3987,7 @@
"resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.2.tgz",
"integrity": "sha512-6mDvHUFSjyT2B2yeNx2nUgMxh9LtOWvkhIU3uePn2I2oyNymUAX1NIsdgviM4CH+JSrp2D2hsMvJOkxY+0wNRA==",
"license": "MIT",
"peer": true,
"dependencies": {
"csstype": "^3.0.2"
}
@ -3993,6 +3998,7 @@
"integrity": "sha512-/EEvYBdT3BflCWvTMO7YkYBHVE9Ci6XdqZciZANQgKpaiDRGOLIlRo91jbTNRQjgPFWVaRxcYc0luVNFitz57A==",
"devOptional": true,
"license": "MIT",
"peer": true,
"peerDependencies": {
"@types/react": "^19.2.0"
}
@ -4080,6 +4086,7 @@
"integrity": "sha512-jCNyAuXx8dr5KJMkecGmZ8KI61KBUhkCob+SD+C+I5+Y1FWI2Y3QmY4/cxMCC5WAsZqoEtEETVhUiUMIGCf6Bw==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@typescript-eslint/scope-manager": "8.40.0",
"@typescript-eslint/types": "8.40.0",
@ -4587,6 +4594,7 @@
"integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
"dev": true,
"license": "MIT",
"peer": true,
"bin": {
"acorn": "bin/acorn"
},
@ -5109,9 +5117,9 @@
"license": "MIT"
},
"node_modules/brace-expansion": {
"version": "1.1.11",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
"integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
"version": "1.1.12",
"resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
"integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
"dev": true,
"license": "MIT",
"dependencies": {
@ -5152,6 +5160,7 @@
}
],
"license": "MIT",
"peer": true,
"dependencies": {
"caniuse-lite": "^1.0.30001716",
"electron-to-chromium": "^1.5.149",
@ -6200,6 +6209,7 @@
"integrity": "sha512-XyLmROnACWqSxiGYArdef1fItQd47weqB7iwtfr9JHwRrqIXZdcFMvvEcL9xHCmL0SNsOvF0c42lWyM1U5dgig==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@eslint-community/eslint-utils": "^4.8.0",
"@eslint-community/regexpp": "^4.12.1",
@ -6289,6 +6299,7 @@
"integrity": "sha512-82GZUjRS0p/jganf6q1rEO25VSoHH0hKPCTrgillPjdI/3bgBhAE1QzHrHTizjpRvy6pGAvKjDJtk2pF9NDq8w==",
"dev": true,
"license": "MIT",
"peer": true,
"bin": {
"eslint-config-prettier": "bin/cli.js"
},
@ -6390,6 +6401,7 @@
"integrity": "sha512-ixmkI62Rbc2/w8Vfxyh1jQRTdRTF52VxwRVHl/ykPAmqG+Nb7/kNn+byLP0LxPgI7zWA16Jt82SybJInmMia3A==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@rtsao/scc": "^1.1.0",
"array-includes": "^3.1.8",
@ -9404,6 +9416,7 @@
"integrity": "sha512-Cvc9WUhxSMEo4McES3P7oK3QaXldCfNWp7pl2NNeiIFlCoLr3kfq9kb1fxftiwk1FLV7CvpvDfonxtzUDeSOPg==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"cssstyle": "^4.2.1",
"data-urls": "^5.0.0",
@ -11805,6 +11818,7 @@
"resolved": "https://registry.npmjs.org/preact/-/preact-10.26.9.tgz",
"integrity": "sha512-SSjF9vcnF27mJK1XyFMNJzFd5u3pQiATFqoaDy03XuN00u4ziveVVEGt5RKJrDR8MHE/wJo9Nnad56RLzS2RMA==",
"license": "MIT",
"peer": true,
"funding": {
"type": "opencollective",
"url": "https://opencollective.com/preact"
@ -11844,6 +11858,7 @@
"integrity": "sha512-I7AIg5boAr5R0FFtJ6rCfD+LFsWHp81dolrFD8S79U9tb8Az2nGrJncnMSnys+bpQJfRUzqs9hnA81OAA3hCuQ==",
"dev": true,
"license": "MIT",
"peer": true,
"bin": {
"prettier": "bin/prettier.cjs"
},
@ -11991,6 +12006,7 @@
"resolved": "https://registry.npmjs.org/react/-/react-19.2.0.tgz",
"integrity": "sha512-tmbWg6W31tQLeB5cdIBOicJDJRR2KzXsV7uSK9iNfLWQ5bIZfxuPEHp7M8wiHyHnn0DD1i7w3Zmin0FtkrwoCQ==",
"license": "MIT",
"peer": true,
"engines": {
"node": ">=0.10.0"
}
@ -12000,6 +12016,7 @@
"resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.0.tgz",
"integrity": "sha512-UlbRu4cAiGaIewkPyiRGJk0imDN2T3JjieT6spoL2UeSf5od4n5LB/mQ4ejmxhCFT1tYe8IvaFulzynWovsEFQ==",
"license": "MIT",
"peer": true,
"dependencies": {
"scheduler": "^0.27.0"
},
@ -13237,6 +13254,7 @@
"integrity": "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg==",
"dev": true,
"license": "MIT",
"peer": true,
"engines": {
"node": ">=12"
},
@ -13342,6 +13360,7 @@
"integrity": "sha512-f0FFpIdcHgn8zcPSbf1dRevwt047YMnaiJM3u2w2RewrB+fob/zePZcrOyQoLMMO7aBIddLcQIEK5dYjkLnGrQ==",
"dev": true,
"license": "MIT",
"peer": true,
"dependencies": {
"@cspotcode/source-map-support": "^0.8.0",
"@tsconfig/node10": "^1.0.7",
@ -13529,6 +13548,7 @@
"integrity": "sha512-CWBzXQrc/qOkhidw1OzBTQuYRbfyxDXJMVJ1XNwUHGROVmuaeiEm3OslpZ1RV96d7SKKjZKrSJu3+t/xlw3R9A==",
"dev": true,
"license": "Apache-2.0",
"peer": true,
"bin": {
"tsc": "bin/tsc",
"tsserver": "bin/tsserver"