diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml
index 87b2d8d..573ef22 100644
--- a/.buildkite/pipeline.yml
+++ b/.buildkite/pipeline.yml
@@ -14,7 +14,7 @@ steps:
           cuda: "*"
           multigpu: "*"
         if: build.message !~ /\[skip tests\]/
-        timeout_in_minutes: 30 
+        timeout_in_minutes: 45
         matrix:
           setup:
             julia:
@@ -37,10 +37,11 @@ steps:
           cuda: "*"
           multigpu: "*"
         if: build.message !~ /\[skip tests\]/ && !build.pull_request.draft
-        timeout_in_minutes: 30
+        timeout_in_minutes: 45
         matrix:
           setup:
             cuda:
+              - "13.0"
               - "12.9"
               - "12.8"
               - "12.6"
@@ -50,11 +51,6 @@ steps:
               - "12.2"
               - "12.1"
               - "12.0"
-              - "11.8"
-              - "11.7"
-              - "11.6"
-              - "11.5"
-              - "11.4"
         commands: |
           echo -e "[extras]\nCUDA_Runtime_jll = \"76a88914-d11a-5bdc-97e0-2f5a05c973a2\"\nCUDA_Driver_jll = \"4ee394cb-3365-5eb0-8335-949819d2adfc\"" >>test/Project.toml
           echo -e "[CUDA_Runtime_jll]\nversion = \"{{matrix.cuda}}\"" >test/LocalPreferences.toml
diff --git a/.github/workflows/Documenter.yml b/.github/workflows/Documenter.yml
index 2955d68..40ead81 100644
--- a/.github/workflows/Documenter.yml
+++ b/.github/workflows/Documenter.yml
@@ -1,7 +1,7 @@
 name: Documenter
 on:
   push:
-    branches: [master]
+    branches: [main, master]
     tags: [v*]
   pull_request:
 
@@ -9,12 +9,17 @@ jobs:
   Documenter:
     permissions:
       contents: write
+      statuses: write
     name: Documentation
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+      - uses: julia-actions/setup-julia@v2
+        with:
+          version: '1'
+          show-versioninfo: true
+      - uses: julia-actions/cache@v2
       - uses: julia-actions/julia-buildpkg@v1
       - uses: julia-actions/julia-docdeploy@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          DOCUMENTER_KEY: ${{ secrets.DOCUMENTER_KEY }}
diff --git a/Project.toml b/Project.toml
index 25456f5..515bc2b 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,6 +1,6 @@
 name = "NCCL"
 uuid = "3fe64909-d7a1-4096-9b7d-7a0f12cf0f6b"
-version = "0.1.1"
+version = "0.1.2"
 
 [deps]
 CEnum = "fa961155-64e5-5f13-b03f-caf6b980ea82"
@@ -10,4 +10,5 @@ NCCL_jll = "4d6d38e4-5b87-5e63-912a-873ff2d649b7"
 [compat]
 CEnum = "0.2, 0.3, 0.4, 0.5"
 CUDA = "5"
+NCCL_jll = "2.28.3"
 julia = "1.10"
diff --git a/docs/Manifest.toml b/docs/Manifest.toml
deleted file mode 100644
index d4588f8..0000000
--- a/docs/Manifest.toml
+++ /dev/null
@@ -1,655 +0,0 @@
-# This file is machine-generated - editing it directly is not advised
-
-julia_version = "1.10.0"
-manifest_format = "2.0"
-project_hash = "831b73d63aaf456e94a12b6c19c53fdd65b198c9"
-
-[[deps.ANSIColoredPrinters]]
-git-tree-sha1 = "574baf8110975760d391c710b6341da1afa48d8c"
-uuid = "a4c015fc-c6ff-483c-b24f-f7ea428134e9"
-version = "0.0.1"
-
-[[deps.AbstractFFTs]]
-deps = ["LinearAlgebra"]
-git-tree-sha1 = "d92ad398961a3ed262d8bf04a1a2b8340f915fef"
-uuid = "621f4979-c628-5d54-868e-fcf4e3e8185c"
-version = "1.5.0"
-
-    [deps.AbstractFFTs.extensions]
-    AbstractFFTsChainRulesCoreExt = "ChainRulesCore"
-    AbstractFFTsTestExt = "Test"
-
-    [deps.AbstractFFTs.weakdeps]
-    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
-    Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
-
-[[deps.AbstractTrees]]
-git-tree-sha1 = "faa260e4cb5aba097a73fab382dd4b5819d8ec8c"
-uuid = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"
-version = "0.4.4"
-
-[[deps.Adapt]]
-deps = ["LinearAlgebra", "Requires"]
-git-tree-sha1 = "cde29ddf7e5726c9fb511f340244ea3481267608"
-uuid = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
-version = "3.7.2"
-weakdeps = ["StaticArrays"]
-
-    [deps.Adapt.extensions]
-    AdaptStaticArraysExt = "StaticArrays"
-
-[[deps.ArgTools]]
-uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
-version = "1.1.1"
-
-[[deps.Artifacts]]
-uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
-
-[[deps.Atomix]]
-deps = ["UnsafeAtomics"]
-git-tree-sha1 = "c06a868224ecba914baa6942988e2f2aade419be"
-uuid = "a9b6321e-bd34-4604-b9c9-b65b8de01458"
-version = "0.1.0"
-
-[[deps.BFloat16s]]
-deps = ["LinearAlgebra", "Printf", "Random", "Test"]
-git-tree-sha1 = "dbf84058d0a8cbbadee18d25cf606934b22d7c66"
-uuid = "ab4f0b2a-ad5b-11e8-123f-65d77653426b"
-version = "0.4.2"
-
-[[deps.Base64]]
-uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
-
-[[deps.CEnum]]
-git-tree-sha1 = "389ad5c84de1ae7cf0e28e381131c98ea87d54fc"
-uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
-version = "0.5.0"
-
-[[deps.CUDA]]
-deps = ["AbstractFFTs", "Adapt", "BFloat16s", "CEnum", "CUDA_Driver_jll", "CUDA_Runtime_Discovery", "CUDA_Runtime_jll", "Crayons", "DataFrames", "ExprTools", "GPUArrays", "GPUCompiler", "KernelAbstractions", "LLVM", "LLVMLoopInfo", "LazyArtifacts", "Libdl", "LinearAlgebra", "Logging", "NVTX", "Preferences", "PrettyTables", "Printf", "Random", "Random123", "RandomNumbers", "Reexport", "Requires", "SparseArrays", "Statistics", "UnsafeAtomicsLLVM"]
-git-tree-sha1 = "76582ae19006b1186e87dadd781747f76cead72c"
-uuid = "052768ef-5323-5732-b1bb-66c8b64840ba"
-version = "5.1.1"
-
-    [deps.CUDA.extensions]
-    ChainRulesCoreExt = "ChainRulesCore"
-    SpecialFunctionsExt = "SpecialFunctions"
-
-    [deps.CUDA.weakdeps]
-    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
-    SpecialFunctions = "276daf66-3868-5448-9aa4-cd146d93841b"
-
-[[deps.CUDA_Driver_jll]]
-deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg"]
-git-tree-sha1 = "1e42ef1bdb45487ff28de16182c0df4920181dc3"
-uuid = "4ee394cb-3365-5eb0-8335-949819d2adfc"
-version = "0.7.0+0"
-
-[[deps.CUDA_Runtime_Discovery]]
-deps = ["Libdl"]
-git-tree-sha1 = "bcc4a23cbbd99c8535a5318455dcf0f2546ec536"
-uuid = "1af6417a-86b4-443c-805f-a4643ffb695f"
-version = "0.2.2"
-
-[[deps.CUDA_Runtime_jll]]
-deps = ["Artifacts", "CUDA_Driver_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "9704e50c9158cf8896c2776b8dbc5edd136caf80"
-uuid = "76a88914-d11a-5bdc-97e0-2f5a05c973a2"
-version = "0.10.1+0"
-
-[[deps.ColorTypes]]
-deps = ["FixedPointNumbers", "Random"]
-git-tree-sha1 = "eb7f0f8307f71fac7c606984ea5fb2817275d6e4"
-uuid = "3da002f7-5984-5a60-b8a6-cbb66c0b333f"
-version = "0.11.4"
-
-[[deps.Colors]]
-deps = ["ColorTypes", "FixedPointNumbers", "Reexport"]
-git-tree-sha1 = "fc08e5930ee9a4e03f84bfb5211cb54e7769758a"
-uuid = "5ae59095-9a9b-59fe-a467-6f913c188581"
-version = "0.12.10"
-
-[[deps.Compat]]
-deps = ["UUIDs"]
-git-tree-sha1 = "886826d76ea9e72b35fcd000e535588f7b60f21d"
-uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
-version = "4.10.1"
-weakdeps = ["Dates", "LinearAlgebra"]
-
-    [deps.Compat.extensions]
-    CompatLinearAlgebraExt = "LinearAlgebra"
-
-[[deps.CompilerSupportLibraries_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
-version = "1.0.5+1"
-
-[[deps.Crayons]]
-git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
-uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
-version = "4.1.1"
-
-[[deps.DataAPI]]
-git-tree-sha1 = "8da84edb865b0b5b0100c0666a9bc9a0b71c553c"
-uuid = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"
-version = "1.15.0"
-
-[[deps.DataFrames]]
-deps = ["Compat", "DataAPI", "DataStructures", "Future", "InlineStrings", "InvertedIndices", "IteratorInterfaceExtensions", "LinearAlgebra", "Markdown", "Missings", "PooledArrays", "PrecompileTools", "PrettyTables", "Printf", "REPL", "Random", "Reexport", "SentinelArrays", "SortingAlgorithms", "Statistics", "TableTraits", "Tables", "Unicode"]
-git-tree-sha1 = "04c738083f29f86e62c8afc341f0967d8717bdb8"
-uuid = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
-version = "1.6.1"
-
-[[deps.DataStructures]]
-deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
-git-tree-sha1 = "3dbd312d370723b6bb43ba9d02fc36abade4518d"
-uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
-version = "0.18.15"
-
-[[deps.DataValueInterfaces]]
-git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
-uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
-version = "1.0.0"
-
-[[deps.Dates]]
-deps = ["Printf"]
-uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
-
-[[deps.DocStringExtensions]]
-deps = ["LibGit2"]
-git-tree-sha1 = "2fb1e02f2b635d0845df5d7c167fec4dd739b00d"
-uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
-version = "0.9.3"
-
-[[deps.Documenter]]
-deps = ["ANSIColoredPrinters", "AbstractTrees", "Base64", "Dates", "DocStringExtensions", "Downloads", "Git", "IOCapture", "InteractiveUtils", "JSON", "LibGit2", "Logging", "Markdown", "MarkdownAST", "Pkg", "PrecompileTools", "REPL", "RegistryInstances", "SHA", "Test", "Unicode"]
-git-tree-sha1 = "2613dbec8f4748273bbe30ba71fd5cb369966bac"
-uuid = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
-version = "1.2.1"
-
-[[deps.Downloads]]
-deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
-uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
-version = "1.6.0"
-
-[[deps.Expat_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl"]
-git-tree-sha1 = "4558ab818dcceaab612d1bb8c19cee87eda2b83c"
-uuid = "2e619515-83b5-522b-bb60-26c02a35a201"
-version = "2.5.0+0"
-
-[[deps.ExprTools]]
-git-tree-sha1 = "27415f162e6028e81c72b82ef756bf321213b6ec"
-uuid = "e2ba6199-217a-4e67-a87a-7c52f15ade04"
-version = "0.1.10"
-
-[[deps.FileWatching]]
-uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
-
-[[deps.FixedPointNumbers]]
-deps = ["Statistics"]
-git-tree-sha1 = "335bfdceacc84c5cdf16aadc768aa5ddfc5383cc"
-uuid = "53c48c17-4a7d-5ca2-90c5-79b7896eea93"
-version = "0.8.4"
-
-[[deps.Future]]
-deps = ["Random"]
-uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
-
-[[deps.GPUArrays]]
-deps = ["Adapt", "GPUArraysCore", "LLVM", "LinearAlgebra", "Printf", "Random", "Reexport", "Serialization", "Statistics"]
-git-tree-sha1 = "85d7fb51afb3def5dcb85ad31c3707795c8bccc1"
-uuid = "0c68f7d7-f131-5f86-a1c3-88cf8149b2d7"
-version = "9.1.0"
-
-[[deps.GPUArraysCore]]
-deps = ["Adapt"]
-git-tree-sha1 = "2d6ca471a6c7b536127afccfa7564b5b39227fe0"
-uuid = "46192b85-c4d5-4398-a991-12ede77f4527"
-version = "0.1.5"
-
-[[deps.GPUCompiler]]
-deps = ["ExprTools", "InteractiveUtils", "LLVM", "Libdl", "Logging", "Scratch", "TimerOutputs", "UUIDs"]
-git-tree-sha1 = "a846f297ce9d09ccba02ead0cae70690e072a119"
-uuid = "61eb1bfa-7361-4325-ad38-22787b887f55"
-version = "0.25.0"
-
-[[deps.Git]]
-deps = ["Git_jll"]
-git-tree-sha1 = "51764e6c2e84c37055e846c516e9015b4a291c7d"
-uuid = "d7ba0133-e1db-5d97-8f8c-041e4b3a1eb2"
-version = "1.3.0"
-
-[[deps.Git_jll]]
-deps = ["Artifacts", "Expat_jll", "JLLWrappers", "LibCURL_jll", "Libdl", "Libiconv_jll", "OpenSSL_jll", "PCRE2_jll", "Zlib_jll"]
-git-tree-sha1 = "bb8f7cc77ec1152414b2af6db533d9471cfbb2d1"
-uuid = "f8c6e375-362e-5223-8a59-34ff63f689eb"
-version = "2.42.0+0"
-
-[[deps.IOCapture]]
-deps = ["Logging", "Random"]
-git-tree-sha1 = "d75853a0bdbfb1ac815478bacd89cd27b550ace6"
-uuid = "b5f81e59-6552-4d32-b1f0-c071b021bf89"
-version = "0.2.3"
-
-[[deps.InlineStrings]]
-deps = ["Parsers"]
-git-tree-sha1 = "9cc2baf75c6d09f9da536ddf58eb2f29dedaf461"
-uuid = "842dd82b-1e85-43dc-bf29-5d0ee9dffc48"
-version = "1.4.0"
-
-[[deps.InteractiveUtils]]
-deps = ["Markdown"]
-uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
-
-[[deps.InvertedIndices]]
-git-tree-sha1 = "0dc7b50b8d436461be01300fd8cd45aa0274b038"
-uuid = "41ab1584-1d38-5bbf-9106-f11c6c58b48f"
-version = "1.3.0"
-
-[[deps.IteratorInterfaceExtensions]]
-git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
-uuid = "82899510-4779-5014-852e-03e436cf321d"
-version = "1.0.0"
-
-[[deps.JLLWrappers]]
-deps = ["Artifacts", "Preferences"]
-git-tree-sha1 = "7e5d6779a1e09a36db2a7b6cff50942a0a7d0fca"
-uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
-version = "1.5.0"
-
-[[deps.JSON]]
-deps = ["Dates", "Mmap", "Parsers", "Unicode"]
-git-tree-sha1 = "31e996f0a15c7b280ba9f76636b3ff9e2ae58c9a"
-uuid = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
-version = "0.21.4"
-
-[[deps.JuliaNVTXCallbacks_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
-git-tree-sha1 = "af433a10f3942e882d3c671aacb203e006a5808f"
-uuid = "9c1d0b0a-7046-5b2e-a33f-ea22f176ac7e"
-version = "0.2.1+0"
-
-[[deps.KernelAbstractions]]
-deps = ["Adapt", "Atomix", "InteractiveUtils", "LinearAlgebra", "MacroTools", "PrecompileTools", "Requires", "SparseArrays", "StaticArrays", "UUIDs", "UnsafeAtomics", "UnsafeAtomicsLLVM"]
-git-tree-sha1 = "653e0824fc9ab55b3beec67a6dbbe514a65fb954"
-uuid = "63c18a36-062a-441e-b654-da1e3ab1ce7c"
-version = "0.9.15"
-
-    [deps.KernelAbstractions.extensions]
-    EnzymeExt = "EnzymeCore"
-
-    [deps.KernelAbstractions.weakdeps]
-    EnzymeCore = "f151be2c-9106-41f4-ab19-57ee4f262869"
-
-[[deps.LLVM]]
-deps = ["CEnum", "LLVMExtra_jll", "Libdl", "Preferences", "Printf", "Requires", "Unicode"]
-git-tree-sha1 = "0678579657515e88b6632a3a482d39adcbb80445"
-uuid = "929cbde3-209d-540e-8aea-75f648917ca0"
-version = "6.4.1"
-weakdeps = ["BFloat16s"]
-
-    [deps.LLVM.extensions]
-    BFloat16sExt = "BFloat16s"
-
-[[deps.LLVMExtra_jll]]
-deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "98eaee04d96d973e79c25d49167668c5c8fb50e2"
-uuid = "dad2f222-ce93-54a1-a47d-0025e8a3acab"
-version = "0.0.27+1"
-
-[[deps.LLVMLoopInfo]]
-git-tree-sha1 = "2e5c102cfc41f48ae4740c7eca7743cc7e7b75ea"
-uuid = "8b046642-f1f6-4319-8d3c-209ddc03c586"
-version = "1.0.0"
-
-[[deps.LaTeXStrings]]
-git-tree-sha1 = "50901ebc375ed41dbf8058da26f9de442febbbec"
-uuid = "b964fa9f-0449-5b57-a5c2-d3ea65f4040f"
-version = "1.3.1"
-
-[[deps.LazilyInitializedFields]]
-git-tree-sha1 = "8f7f3cabab0fd1800699663533b6d5cb3fc0e612"
-uuid = "0e77f7df-68c5-4e49-93ce-4cd80f5598bf"
-version = "1.2.2"
-
-[[deps.LazyArtifacts]]
-deps = ["Artifacts", "Pkg"]
-uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
-
-[[deps.LibCURL]]
-deps = ["LibCURL_jll", "MozillaCACerts_jll"]
-uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
-version = "0.6.4"
-
-[[deps.LibCURL_jll]]
-deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
-uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
-version = "8.4.0+0"
-
-[[deps.LibGit2]]
-deps = ["Base64", "LibGit2_jll", "NetworkOptions", "Printf", "SHA"]
-uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
-
-[[deps.LibGit2_jll]]
-deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll"]
-uuid = "e37daf67-58a4-590a-8e99-b0245dd2ffc5"
-version = "1.6.4+0"
-
-[[deps.LibSSH2_jll]]
-deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
-uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
-version = "1.11.0+1"
-
-[[deps.Libdl]]
-uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
-
-[[deps.Libiconv_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl"]
-git-tree-sha1 = "f9557a255370125b405568f9767d6d195822a175"
-uuid = "94ce4f54-9a6c-5748-9c1c-f9c7231a4531"
-version = "1.17.0+0"
-
-[[deps.LinearAlgebra]]
-deps = ["Libdl", "OpenBLAS_jll", "libblastrampoline_jll"]
-uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
-
-[[deps.Logging]]
-uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
-
-[[deps.MacroTools]]
-deps = ["Markdown", "Random"]
-git-tree-sha1 = "b211c553c199c111d998ecdaf7623d1b89b69f93"
-uuid = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
-version = "0.5.12"
-
-[[deps.Markdown]]
-deps = ["Base64"]
-uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
-
-[[deps.MarkdownAST]]
-deps = ["AbstractTrees", "Markdown"]
-git-tree-sha1 = "465a70f0fc7d443a00dcdc3267a497397b8a3899"
-uuid = "d0879d2d-cac2-40c8-9cee-1863dc0c7391"
-version = "0.1.2"
-
-[[deps.MbedTLS_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
-version = "2.28.2+1"
-
-[[deps.Missings]]
-deps = ["DataAPI"]
-git-tree-sha1 = "f66bdc5de519e8f8ae43bdc598782d35a25b1272"
-uuid = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
-version = "1.1.0"
-
-[[deps.Mmap]]
-uuid = "a63ad114-7e13-5084-954f-fe012c677804"
-
-[[deps.MozillaCACerts_jll]]
-uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
-version = "2023.1.10"
-
-[[deps.NCCL]]
-deps = ["CEnum", "CUDA", "NCCL_jll"]
-path = ".."
-uuid = "3fe64909-d7a1-4096-9b7d-7a0f12cf0f6b"
-version = "0.2.0"
-
-[[deps.NCCL_jll]]
-deps = ["Artifacts", "CUDA_Runtime_jll", "CompilerSupportLibraries_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "9dcc505d4c7267cb4e1904b3c3f8049ef61d0b4a"
-uuid = "4d6d38e4-5b87-5e63-912a-873ff2d649b7"
-version = "2.19.4+0"
-
-[[deps.NVTX]]
-deps = ["Colors", "JuliaNVTXCallbacks_jll", "Libdl", "NVTX_jll"]
-git-tree-sha1 = "8bc9ce4233be3c63f8dcd78ccaf1b63a9c0baa34"
-uuid = "5da4648a-3479-48b8-97b9-01cb529c0a1f"
-version = "0.3.3"
-
-[[deps.NVTX_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
-git-tree-sha1 = "ce3269ed42816bf18d500c9f63418d4b0d9f5a3b"
-uuid = "e98f9f5b-d649-5603-91fd-7774390e6439"
-version = "3.1.0+2"
-
-[[deps.NetworkOptions]]
-uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
-version = "1.2.0"
-
-[[deps.OpenBLAS_jll]]
-deps = ["Artifacts", "CompilerSupportLibraries_jll", "Libdl"]
-uuid = "4536629a-c528-5b80-bd46-f80d51c5b363"
-version = "0.3.23+2"
-
-[[deps.OpenSSL_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl"]
-git-tree-sha1 = "cc6e1927ac521b659af340e0ca45828a3ffc748f"
-uuid = "458c3c95-2e84-50aa-8efc-19380b2a3a95"
-version = "3.0.12+0"
-
-[[deps.OrderedCollections]]
-git-tree-sha1 = "dfdf5519f235516220579f949664f1bf44e741c5"
-uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-version = "1.6.3"
-
-[[deps.PCRE2_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "efcefdf7-47ab-520b-bdef-62a2eaa19f15"
-version = "10.42.0+1"
-
-[[deps.Parsers]]
-deps = ["Dates", "PrecompileTools", "UUIDs"]
-git-tree-sha1 = "8489905bcdbcfac64d1daa51ca07c0d8f0283821"
-uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
-version = "2.8.1"
-
-[[deps.Pkg]]
-deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
-uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
-version = "1.10.0"
-
-[[deps.PooledArrays]]
-deps = ["DataAPI", "Future"]
-git-tree-sha1 = "36d8b4b899628fb92c2749eb488d884a926614d3"
-uuid = "2dfb63ee-cc39-5dd5-95bd-886bf059d720"
-version = "1.4.3"
-
-[[deps.PrecompileTools]]
-deps = ["Preferences"]
-git-tree-sha1 = "03b4c25b43cb84cee5c90aa9b5ea0a78fd848d2f"
-uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
-version = "1.2.0"
-
-[[deps.Preferences]]
-deps = ["TOML"]
-git-tree-sha1 = "00805cd429dcb4870060ff49ef443486c262e38e"
-uuid = "21216c6a-2e73-6563-6e65-726566657250"
-version = "1.4.1"
-
-[[deps.PrettyTables]]
-deps = ["Crayons", "LaTeXStrings", "Markdown", "PrecompileTools", "Printf", "Reexport", "StringManipulation", "Tables"]
-git-tree-sha1 = "88b895d13d53b5577fd53379d913b9ab9ac82660"
-uuid = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
-version = "2.3.1"
-
-[[deps.Printf]]
-deps = ["Unicode"]
-uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
-
-[[deps.REPL]]
-deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
-uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
-
-[[deps.Random]]
-deps = ["SHA"]
-uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-
-[[deps.Random123]]
-deps = ["Random", "RandomNumbers"]
-git-tree-sha1 = "c860e84651f58ce240dd79e5d9e055d55234c35a"
-uuid = "74087812-796a-5b5d-8853-05524746bad3"
-version = "1.6.2"
-
-[[deps.RandomNumbers]]
-deps = ["Random", "Requires"]
-git-tree-sha1 = "043da614cc7e95c703498a491e2c21f58a2b8111"
-uuid = "e6cf234a-135c-5ec9-84dd-332b85af5143"
-version = "1.5.3"
-
-[[deps.Reexport]]
-git-tree-sha1 = "45e428421666073eab6f2da5c9d310d99bb12f9b"
-uuid = "189a3867-3050-52da-a836-e630ba90ab69"
-version = "1.2.2"
-
-[[deps.RegistryInstances]]
-deps = ["LazilyInitializedFields", "Pkg", "TOML", "Tar"]
-git-tree-sha1 = "ffd19052caf598b8653b99404058fce14828be51"
-uuid = "2792f1a3-b283-48e8-9a74-f99dce5104f3"
-version = "0.1.0"
-
-[[deps.Requires]]
-deps = ["UUIDs"]
-git-tree-sha1 = "838a3a4188e2ded87a4f9f184b4b0d78a1e91cb7"
-uuid = "ae029012-a4dd-5104-9daa-d747884805df"
-version = "1.3.0"
-
-[[deps.SHA]]
-uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
-version = "0.7.0"
-
-[[deps.Scratch]]
-deps = ["Dates"]
-git-tree-sha1 = "3bac05bc7e74a75fd9cba4295cde4045d9fe2386"
-uuid = "6c6a2e73-6563-6170-7368-637461726353"
-version = "1.2.1"
-
-[[deps.SentinelArrays]]
-deps = ["Dates", "Random"]
-git-tree-sha1 = "0e7508ff27ba32f26cd459474ca2ede1bc10991f"
-uuid = "91c51154-3ec4-41a3-a24f-3f23e20d615c"
-version = "1.4.1"
-
-[[deps.Serialization]]
-uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
-
-[[deps.Sockets]]
-uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
-
-[[deps.SortingAlgorithms]]
-deps = ["DataStructures"]
-git-tree-sha1 = "5165dfb9fd131cf0c6957a3a7605dede376e7b63"
-uuid = "a2af1166-a08f-5f64-846c-94a0d3cef48c"
-version = "1.2.0"
-
-[[deps.SparseArrays]]
-deps = ["Libdl", "LinearAlgebra", "Random", "Serialization", "SuiteSparse_jll"]
-uuid = "2f01184e-e22b-5df5-ae63-d93ebab69eaf"
-version = "1.10.0"
-
-[[deps.StaticArrays]]
-deps = ["LinearAlgebra", "PrecompileTools", "Random", "StaticArraysCore"]
-git-tree-sha1 = "fba11dbe2562eecdfcac49a05246af09ee64d055"
-uuid = "90137ffa-7385-5640-81b9-e52037218182"
-version = "1.8.1"
-
-    [deps.StaticArrays.extensions]
-    StaticArraysChainRulesCoreExt = "ChainRulesCore"
-    StaticArraysStatisticsExt = "Statistics"
-
-    [deps.StaticArrays.weakdeps]
-    ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
-    Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
-
-[[deps.StaticArraysCore]]
-git-tree-sha1 = "36b3d696ce6366023a0ea192b4cd442268995a0d"
-uuid = "1e83bf80-4336-4d27-bf5d-d5a4f845583c"
-version = "1.4.2"
-
-[[deps.Statistics]]
-deps = ["LinearAlgebra", "SparseArrays"]
-uuid = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
-version = "1.10.0"
-
-[[deps.StringManipulation]]
-deps = ["PrecompileTools"]
-git-tree-sha1 = "a04cabe79c5f01f4d723cc6704070ada0b9d46d5"
-uuid = "892a3eda-7b42-436c-8928-eab12a02cf0e"
-version = "0.3.4"
-
-[[deps.SuiteSparse_jll]]
-deps = ["Artifacts", "Libdl", "libblastrampoline_jll"]
-uuid = "bea87d4a-7f5b-5778-9afe-8cc45184846c"
-version = "7.2.1+1"
-
-[[deps.TOML]]
-deps = ["Dates"]
-uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
-version = "1.0.3"
-
-[[deps.TableTraits]]
-deps = ["IteratorInterfaceExtensions"]
-git-tree-sha1 = "c06b2f539df1c6efa794486abfb6ed2022561a39"
-uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
-version = "1.0.1"
-
-[[deps.Tables]]
-deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "LinearAlgebra", "OrderedCollections", "TableTraits"]
-git-tree-sha1 = "cb76cf677714c095e535e3501ac7954732aeea2d"
-uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
-version = "1.11.1"
-
-[[deps.Tar]]
-deps = ["ArgTools", "SHA"]
-uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
-version = "1.10.0"
-
-[[deps.Test]]
-deps = ["InteractiveUtils", "Logging", "Random", "Serialization"]
-uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
-
-[[deps.TimerOutputs]]
-deps = ["ExprTools", "Printf"]
-git-tree-sha1 = "f548a9e9c490030e545f72074a41edfd0e5bcdd7"
-uuid = "a759f4b9-e2f1-59dc-863e-4aeb61b1ea8f"
-version = "0.5.23"
-
-[[deps.UUIDs]]
-deps = ["Random", "SHA"]
-uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
-
-[[deps.Unicode]]
-uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
-
-[[deps.UnsafeAtomics]]
-git-tree-sha1 = "6331ac3440856ea1988316b46045303bef658278"
-uuid = "013be700-e6cd-48c3-b4a1-df204f14c38f"
-version = "0.2.1"
-
-[[deps.UnsafeAtomicsLLVM]]
-deps = ["LLVM", "UnsafeAtomics"]
-git-tree-sha1 = "323e3d0acf5e78a56dfae7bd8928c989b4f3083e"
-uuid = "d80eeb9a-aca5-4d75-85e5-170c8b632249"
-version = "0.1.3"
-
-[[deps.Zlib_jll]]
-deps = ["Libdl"]
-uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
-version = "1.2.13+1"
-
-[[deps.libblastrampoline_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "8e850b90-86db-534c-a0d3-1478176c7d93"
-version = "5.8.0+1"
-
-[[deps.nghttp2_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
-version = "1.52.0+1"
-
-[[deps.p7zip_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
-version = "17.4.0+2"
diff --git a/docs/Project.toml b/docs/Project.toml
index 4e8da11..7c0385e 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -2,3 +2,6 @@
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 NCCL = "3fe64909-d7a1-4096-9b7d-7a0f12cf0f6b"
+
+[sources]
+NCCL = { path = ".." }
diff --git a/res/wrap/Manifest.toml b/res/wrap/Manifest.toml
index 556b402..6b1f713 100644
--- a/res/wrap/Manifest.toml
+++ b/res/wrap/Manifest.toml
@@ -1,92 +1,65 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.9.4"
+julia_version = "1.11.6"
 manifest_format = "2.0"
 project_hash = "c24c6cc39efbdedbfd117abf2a3fb1c76d6d6317"
 
 [[deps.ArgTools]]
 uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
-version = "1.1.1"
+version = "1.1.2"
 
 [[deps.Artifacts]]
 uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
+version = "1.11.0"
 
 [[deps.Base64]]
 uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
+version = "1.11.0"
 
 [[deps.CEnum]]
-git-tree-sha1 = "eb4cb44a499229b3b8426dcfb5dd85333951ff90"
+git-tree-sha1 = "389ad5c84de1ae7cf0e28e381131c98ea87d54fc"
 uuid = "fa961155-64e5-5f13-b03f-caf6b980ea82"
-version = "0.4.2"
-
-[[deps.CSTParser]]
-deps = ["Tokenize"]
-git-tree-sha1 = "3ddd48d200eb8ddf9cb3e0189fc059fd49b97c1f"
-uuid = "00ebfdb7-1f24-5e51-bd34-a7502290713f"
-version = "3.3.6"
+version = "0.5.0"
 
 [[deps.CUDA_Driver_jll]]
-deps = ["Artifacts", "JLLWrappers", "LazyArtifacts", "Libdl", "Pkg"]
-git-tree-sha1 = "1e42ef1bdb45487ff28de16182c0df4920181dc3"
+deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg"]
+git-tree-sha1 = "e6a1d9f5518122c186fd27786b61d2053cfa1b0c"
 uuid = "4ee394cb-3365-5eb0-8335-949819d2adfc"
-version = "0.7.0+0"
+version = "13.0.1+0"
 
 [[deps.CUDA_Runtime_jll]]
 deps = ["Artifacts", "CUDA_Driver_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "9704e50c9158cf8896c2776b8dbc5edd136caf80"
+git-tree-sha1 = "e24c6de116c0735c37e83b8bc05ed60d4d359693"
 uuid = "76a88914-d11a-5bdc-97e0-2f5a05c973a2"
-version = "0.10.1+0"
+version = "0.19.1+0"
 
 [[deps.Clang]]
 deps = ["CEnum", "Clang_jll", "Downloads", "Pkg", "TOML"]
-git-tree-sha1 = "17e51c980e1797210f30155d18ea5a2f02b80833"
+git-tree-sha1 = "6bf09af911d9df84656ddd0c02b5e449c18adba8"
 uuid = "40e3b903-d033-50b4-a0cc-940c62c95e31"
-version = "0.17.7"
+version = "0.19.0"
 
 [[deps.Clang_jll]]
-deps = ["Artifacts", "JLLWrappers", "Libdl", "Pkg", "TOML", "Zlib_jll", "libLLVM_jll"]
-git-tree-sha1 = "124bb00d4ceace456054f17c7cb01e5c8195c609"
+deps = ["Artifacts", "JLLWrappers", "Libdl", "TOML", "Zlib_jll", "libLLVM_jll"]
+git-tree-sha1 = "ebfc8e89823ec2c85ed9fedabe52db149da4c5ec"
 uuid = "0ee61d77-7f21-5576-8119-9fcc46b10100"
-version = "14.0.6+4"
+version = "16.0.6+5"
 
 [[deps.CommonMark]]
-deps = ["Crayons", "JSON", "PrecompileTools", "URIs"]
-git-tree-sha1 = "532c4185d3c9037c0237546d817858b23cf9e071"
+deps = ["PrecompileTools"]
+git-tree-sha1 = "351d6f4eaf273b753001b2de4dffb8279b100769"
 uuid = "a80b9123-70ca-4bc0-993e-6e3bcb318db6"
-version = "0.8.12"
-
-[[deps.Compat]]
-deps = ["UUIDs"]
-git-tree-sha1 = "886826d76ea9e72b35fcd000e535588f7b60f21d"
-uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
-version = "4.10.1"
-
-    [deps.Compat.extensions]
-    CompatLinearAlgebraExt = "LinearAlgebra"
-
-    [deps.Compat.weakdeps]
-    Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
-    LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
+version = "0.9.1"
 
 [[deps.CompilerSupportLibraries_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "e66e0078-7015-5450-92f7-15fbd957f2ae"
-version = "1.0.5+0"
-
-[[deps.Crayons]]
-git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
-uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
-version = "4.1.1"
-
-[[deps.DataStructures]]
-deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
-git-tree-sha1 = "3dbd312d370723b6bb43ba9d02fc36abade4518d"
-uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
-version = "0.18.15"
+version = "1.1.1+0"
 
 [[deps.Dates]]
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
+version = "1.11.0"
 
 [[deps.Downloads]]
 deps = ["ArgTools", "FileWatching", "LibCURL", "NetworkOptions"]
@@ -95,37 +68,34 @@ version = "1.6.0"
 
 [[deps.FileWatching]]
 uuid = "7b1f6079-737a-58dc-b8bc-7a2ca5c1b5ee"
+version = "1.11.0"
 
 [[deps.Glob]]
 git-tree-sha1 = "97285bbd5230dd766e9ef6749b80fc617126d496"
 uuid = "c27321d9-0574-5035-807b-f59d2c89b15c"
 version = "1.3.1"
 
-[[deps.InteractiveUtils]]
-deps = ["Markdown"]
-uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
-
 [[deps.JLLWrappers]]
 deps = ["Artifacts", "Preferences"]
-git-tree-sha1 = "7e5d6779a1e09a36db2a7b6cff50942a0a7d0fca"
+git-tree-sha1 = "0533e564aae234aff59ab625543145446d8b6ec2"
 uuid = "692b3bcd-3c85-4b1f-b108-f13ce0eb3210"
-version = "1.5.0"
-
-[[deps.JSON]]
-deps = ["Dates", "Mmap", "Parsers", "Unicode"]
-git-tree-sha1 = "31e996f0a15c7b280ba9f76636b3ff9e2ae58c9a"
-uuid = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
-version = "0.21.4"
+version = "1.7.1"
 
 [[deps.JuliaFormatter]]
-deps = ["CSTParser", "CommonMark", "DataStructures", "Glob", "Pkg", "PrecompileTools", "Tokenize"]
-git-tree-sha1 = "8f5295e46f594ad2d8652f1098488a77460080cd"
+deps = ["CommonMark", "Glob", "JuliaSyntax", "PrecompileTools", "TOML"]
+git-tree-sha1 = "f512fefd5fdc7dd1ca05778f08f91e9e4c9fdc37"
 uuid = "98e50ef6-434e-11e9-1051-2b60c6c9e899"
-version = "1.0.45"
+version = "2.1.6"
+
+[[deps.JuliaSyntax]]
+git-tree-sha1 = "937da4713526b96ac9a178e2035019d3b78ead4a"
+uuid = "70703baa-626e-46a2-a12c-08ffd08c73b4"
+version = "0.4.10"
 
 [[deps.LazyArtifacts]]
 deps = ["Artifacts", "Pkg"]
 uuid = "4af54fe1-eca0-43a8-85a7-787d91b784e3"
+version = "1.11.0"
 
 [[deps.LibCURL]]
 deps = ["LibCURL_jll", "MozillaCACerts_jll"]
@@ -135,11 +105,17 @@ version = "0.6.4"
 [[deps.LibCURL_jll]]
 deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
 uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
-version = "8.4.0+0"
+version = "8.6.0+0"
 
 [[deps.LibGit2]]
-deps = ["Base64", "NetworkOptions", "Printf", "SHA"]
+deps = ["Base64", "LibGit2_jll", "NetworkOptions", "Printf", "SHA"]
 uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
+version = "1.11.0"
+
+[[deps.LibGit2_jll]]
+deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll"]
+uuid = "e37daf67-58a4-590a-8e99-b0245dd2ffc5"
+version = "1.7.2+0"
 
 [[deps.LibSSH2_jll]]
 deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
@@ -148,86 +124,73 @@ version = "1.11.0+1"
 
 [[deps.Libdl]]
 uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
+version = "1.11.0"
 
 [[deps.Logging]]
 uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
+version = "1.11.0"
 
 [[deps.Markdown]]
 deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
+version = "1.11.0"
 
 [[deps.MbedTLS_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
-version = "2.28.2+0"
-
-[[deps.Mmap]]
-uuid = "a63ad114-7e13-5084-954f-fe012c677804"
+version = "2.28.6+0"
 
 [[deps.MozillaCACerts_jll]]
 uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
-version = "2022.10.11"
+version = "2023.12.12"
 
 [[deps.NCCL_jll]]
-deps = ["Artifacts", "CUDA_Runtime_jll", "CompilerSupportLibraries_jll", "JLLWrappers", "LazyArtifacts", "Libdl", "TOML"]
-git-tree-sha1 = "9dcc505d4c7267cb4e1904b3c3f8049ef61d0b4a"
+deps = ["Artifacts", "CUDA_Runtime_jll", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl", "TOML"]
+git-tree-sha1 = "65dcb2da4acfa4d0db26d49ab14fc22192cf12f7"
 uuid = "4d6d38e4-5b87-5e63-912a-873ff2d649b7"
-version = "2.19.4+0"
+version = "2.28.3+0"
 
 [[deps.NetworkOptions]]
 uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
 version = "1.2.0"
 
-[[deps.OrderedCollections]]
-git-tree-sha1 = "dfdf5519f235516220579f949664f1bf44e741c5"
-uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-version = "1.6.3"
-
-[[deps.Parsers]]
-deps = ["Dates", "PrecompileTools", "UUIDs"]
-git-tree-sha1 = "a935806434c9d4c506ba941871b327b96d41f2bf"
-uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
-version = "2.8.0"
-
 [[deps.Pkg]]
-deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
+deps = ["Artifacts", "Dates", "Downloads", "FileWatching", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "Random", "SHA", "TOML", "Tar", "UUIDs", "p7zip_jll"]
 uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
-version = "1.9.2"
+version = "1.11.0"
+
+    [deps.Pkg.extensions]
+    REPLExt = "REPL"
+
+    [deps.Pkg.weakdeps]
+    REPL = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
 
 [[deps.PrecompileTools]]
 deps = ["Preferences"]
-git-tree-sha1 = "03b4c25b43cb84cee5c90aa9b5ea0a78fd848d2f"
+git-tree-sha1 = "5aa36f7049a63a1528fe8f7c3f2113413ffd4e1f"
 uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
-version = "1.2.0"
+version = "1.2.1"
 
 [[deps.Preferences]]
 deps = ["TOML"]
-git-tree-sha1 = "00805cd429dcb4870060ff49ef443486c262e38e"
+git-tree-sha1 = "0f27480397253da18fe2c12a4ba4eb9eb208bf3d"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
-version = "1.4.1"
+version = "1.5.0"
 
 [[deps.Printf]]
 deps = ["Unicode"]
 uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
-
-[[deps.REPL]]
-deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
-uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
+version = "1.11.0"
 
 [[deps.Random]]
-deps = ["SHA", "Serialization"]
+deps = ["SHA"]
 uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
+version = "1.11.0"
 
 [[deps.SHA]]
 uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
 version = "0.7.0"
 
-[[deps.Serialization]]
-uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
-
-[[deps.Sockets]]
-uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
-
 [[deps.TOML]]
 deps = ["Dates"]
 uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
@@ -238,39 +201,31 @@ deps = ["ArgTools", "SHA"]
 uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
 version = "1.10.0"
 
-[[deps.Tokenize]]
-git-tree-sha1 = "0454d9a9bad2400c7ccad19ca832a2ef5a8bc3a1"
-uuid = "0796e94c-ce3b-5d07-9a54-7f471281c624"
-version = "0.5.26"
-
-[[deps.URIs]]
-git-tree-sha1 = "67db6cc7b3821e19ebe75791a9dd19c9b1188f2b"
-uuid = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
-version = "1.5.1"
-
 [[deps.UUIDs]]
 deps = ["Random", "SHA"]
 uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
+version = "1.11.0"
 
 [[deps.Unicode]]
 uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
+version = "1.11.0"
 
 [[deps.Zlib_jll]]
 deps = ["Libdl"]
 uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
-version = "1.2.13+0"
+version = "1.2.13+1"
 
 [[deps.libLLVM_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "8f36deef-c2a5-5394-99ed-8e07531fb29a"
-version = "14.0.6+3"
+version = "16.0.6+5"
 
 [[deps.nghttp2_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
-version = "1.52.0+1"
+version = "1.59.0+0"
 
 [[deps.p7zip_jll]]
 deps = ["Artifacts", "Libdl"]
 uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"
-version = "17.4.0+0"
+version = "17.4.0+2"
diff --git a/res/wrap/prologue.jl b/res/wrap/prologue.jl
index 157752d..c14e13c 100644
--- a/res/wrap/prologue.jl
+++ b/res/wrap/prologue.jl
@@ -1,8 +1,7 @@
 const NULL = C_NULL
 const INT_MIN = typemin(Cint)
 
-import CUDA.APIUtils: @checked
-import CUDA: CuPtr, CUstream
+import CUDA: @checked, CuPtr, CUstream
 
 function check(f)
     res = f()::ncclResult_t
diff --git a/src/libnccl.jl b/src/libnccl.jl
index 16c36ba..c61216b 100644
--- a/src/libnccl.jl
+++ b/src/libnccl.jl
@@ -3,7 +3,7 @@ module LibNCCL
 using NCCL_jll
 export NCCL_jll
 
-using CEnum
+using CEnum: CEnum, @cenum
 
 const NULL = C_NULL
 const INT_MIN = typemin(Cint)
@@ -13,12 +13,12 @@ import CUDA: @checked, CuPtr, CUstream
 function check(f)
     res = f()::ncclResult_t
     if res != ncclSuccess
-        throw(NCCLError(res))
+        throw(NCCLError(err))
     end
     return
 end
 
-struct ncclConfig_v21700
+struct ncclConfig_v22800
     size::Cint
     magic::Cuint
     version::Cuint
@@ -28,14 +28,35 @@ struct ncclConfig_v21700
     maxCTAs::Cint
     netName::Cstring
     splitShare::Cint
+    trafficClass::Cint
+    commName::Cstring
+    collnetEnable::Cint
+    CTAPolicy::Cint
+    shrinkShare::Cint
+    nvlsCTAs::Cint
+    nChannelsPerNetPeer::Cint
+    nvlinkCentricSched::Cint
 end
 
-const ncclConfig_t = ncclConfig_v21700
+const ncclConfig_t = ncclConfig_v22800
+
+struct ncclSimInfo_v22200
+    size::Cint
+    magic::Cuint
+    version::Cuint
+    estimatedTime::Cfloat
+end
+
+const ncclSimInfo_t = ncclSimInfo_v22200
 
 mutable struct ncclComm end
 
 const ncclComm_t = Ptr{ncclComm}
 
+mutable struct ncclWindow_vidmem end
+
+const ncclWindow_t = Ptr{ncclWindow_vidmem}
+
 struct ncclUniqueId
     internal::NTuple{128,Cchar}
 end
@@ -152,6 +173,36 @@ end
                                   config::Ptr{ncclConfig_t})::ncclResult_t
 end
 
+@checked function ncclCommShrink(comm, excludeRanksList, excludeRanksCount, newcomm, config,
+                                 shrinkFlags)
+    @ccall libnccl.ncclCommShrink(comm::ncclComm_t, excludeRanksList::Ptr{Cint},
+                                  excludeRanksCount::Cint, newcomm::Ptr{ncclComm_t},
+                                  config::Ptr{ncclConfig_t},
+                                  shrinkFlags::Cint)::ncclResult_t
+end
+
+@checked function pncclCommShrink(comm, excludeRanksList, excludeRanksCount, newcomm,
+                                  config, shrinkFlags)
+    @ccall libnccl.pncclCommShrink(comm::ncclComm_t, excludeRanksList::Ptr{Cint},
+                                   excludeRanksCount::Cint, newcomm::Ptr{ncclComm_t},
+                                   config::Ptr{ncclConfig_t},
+                                   shrinkFlags::Cint)::ncclResult_t
+end
+
+@checked function ncclCommInitRankScalable(newcomm, nranks, myrank, nId, commIds, config)
+    @ccall libnccl.ncclCommInitRankScalable(newcomm::Ptr{ncclComm_t}, nranks::Cint,
+                                            myrank::Cint, nId::Cint,
+                                            commIds::Ptr{ncclUniqueId},
+                                            config::Ptr{ncclConfig_t})::ncclResult_t
+end
+
+@checked function pncclCommInitRankScalable(newcomm, nranks, myrank, nId, commIds, config)
+    @ccall libnccl.pncclCommInitRankScalable(newcomm::Ptr{ncclComm_t}, nranks::Cint,
+                                             myrank::Cint, nId::Cint,
+                                             commIds::Ptr{ncclUniqueId},
+                                             config::Ptr{ncclConfig_t})::ncclResult_t
+end
+
 function ncclGetErrorString(result)
     @ccall libnccl.ncclGetErrorString(result::ncclResult_t)::Cstring
 end
@@ -168,6 +219,16 @@ function pncclGetLastError(comm)
     @ccall libnccl.pncclGetLastError(comm::ncclComm_t)::Cstring
 end
 
+# no prototype is found for this function at nccl.h:232:7, please use with caution
+function ncclResetDebugInit()
+    @ccall libnccl.ncclResetDebugInit()::Cvoid
+end
+
+# no prototype is found for this function at nccl.h:234:6, please use with caution
+function pncclResetDebugInit()
+    @ccall libnccl.pncclResetDebugInit()::Cvoid
+end
+
 @checked function ncclCommGetAsyncError(comm, asyncError)
     @ccall libnccl.ncclCommGetAsyncError(comm::ncclComm_t,
                                          asyncError::Ptr{ncclResult_t})::ncclResult_t
@@ -202,6 +263,46 @@ end
     @ccall libnccl.pncclCommUserRank(comm::ncclComm_t, rank::Ptr{Cint})::ncclResult_t
 end
 
+@checked function ncclCommRegister(comm, buff, size, handle)
+    @ccall libnccl.ncclCommRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
+                                    handle::Ptr{Ptr{Cvoid}})::ncclResult_t
+end
+
+@checked function pncclCommRegister(comm, buff, size, handle)
+    @ccall libnccl.pncclCommRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
+                                     handle::Ptr{Ptr{Cvoid}})::ncclResult_t
+end
+
+@checked function ncclCommDeregister(comm, handle)
+    @ccall libnccl.ncclCommDeregister(comm::ncclComm_t, handle::CuPtr{Cvoid})::ncclResult_t
+end
+
+@checked function pncclCommDeregister(comm, handle)
+    @ccall libnccl.pncclCommDeregister(comm::ncclComm_t, handle::CuPtr{Cvoid})::ncclResult_t
+end
+
+@checked function ncclCommWindowRegister(comm, buff, size, win, winFlags)
+    @ccall libnccl.ncclCommWindowRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
+                                          win::Ptr{ncclWindow_t},
+                                          winFlags::Cint)::ncclResult_t
+end
+
+@checked function pncclCommWindowRegister(comm, buff, size, win, winFlags)
+    @ccall libnccl.pncclCommWindowRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
+                                           win::Ptr{ncclWindow_t},
+                                           winFlags::Cint)::ncclResult_t
+end
+
+@checked function ncclCommWindowDeregister(comm, win)
+    @ccall libnccl.ncclCommWindowDeregister(comm::ncclComm_t,
+                                            win::ncclWindow_t)::ncclResult_t
+end
+
+@checked function pncclCommWindowDeregister(comm, win)
+    @ccall libnccl.pncclCommWindowDeregister(comm::ncclComm_t,
+                                             win::ncclWindow_t)::ncclResult_t
+end
+
 @cenum ncclRedOp_dummy_t::UInt32 begin
     ncclNumOps_dummy = 5
 end
@@ -231,7 +332,10 @@ end
     ncclFloat = 7
     ncclFloat64 = 8
     ncclDouble = 8
-    ncclNumTypes = 9
+    ncclBfloat16 = 9
+    ncclFloat8e4m3 = 10
+    ncclFloat8e5m2 = 11
+    ncclNumTypes = 12
 end
 
 @cenum ncclScalarResidence_t::UInt32 begin
@@ -335,6 +439,42 @@ end
                                   comm::ncclComm_t, stream::CUstream)::ncclResult_t
 end
 
+@checked function ncclAlltoAll(sendbuff, recvbuff, count, datatype, comm, stream)
+    @ccall libnccl.ncclAlltoAll(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid}, count::Cint,
+                                datatype::ncclDataType_t, comm::ncclComm_t,
+                                stream::CUstream)::ncclResult_t
+end
+
+@checked function pncclAlltoAll(sendbuff, recvbuff, count, datatype, comm, stream)
+    @ccall libnccl.pncclAlltoAll(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid},
+                                 count::Cint, datatype::ncclDataType_t, comm::ncclComm_t,
+                                 stream::CUstream)::ncclResult_t
+end
+
+@checked function ncclGather(sendbuff, recvbuff, count, datatype, root, comm, stream)
+    @ccall libnccl.ncclGather(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid}, count::Cint,
+                              datatype::ncclDataType_t, root::Cint, comm::ncclComm_t,
+                              stream::CUstream)::ncclResult_t
+end
+
+@checked function pncclGather(sendbuff, recvbuff, count, datatype, root, comm, stream)
+    @ccall libnccl.pncclGather(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid}, count::Cint,
+                               datatype::ncclDataType_t, root::Cint, comm::ncclComm_t,
+                               stream::CUstream)::ncclResult_t
+end
+
+@checked function ncclScatter(sendbuff, recvbuff, count, datatype, root, comm, stream)
+    @ccall libnccl.ncclScatter(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid}, count::Cint,
+                               datatype::ncclDataType_t, root::Cint, comm::ncclComm_t,
+                               stream::CUstream)::ncclResult_t
+end
+
+@checked function pncclScatter(sendbuff, recvbuff, count, datatype, root, comm, stream)
+    @ccall libnccl.pncclScatter(sendbuff::CuPtr{Cvoid}, recvbuff::CuPtr{Cvoid}, count::Cint,
+                                datatype::ncclDataType_t, root::Cint, comm::ncclComm_t,
+                                stream::CUstream)::ncclResult_t
+end
+
 @checked function ncclSend(sendbuff, count, datatype, peer, comm, stream)
     @ccall libnccl.ncclSend(sendbuff::CuPtr{Cvoid}, count::Cint, datatype::ncclDataType_t,
                             peer::Cint, comm::ncclComm_t, stream::CUstream)::ncclResult_t
@@ -355,53 +495,43 @@ end
                             peer::Cint, comm::ncclComm_t, stream::CUstream)::ncclResult_t
 end
 
-# no prototype is found for this function at nccl.h:416:15, please use with caution
+# no prototype is found for this function at nccl.h:546:15, please use with caution
 @checked function ncclGroupStart()
     @ccall libnccl.ncclGroupStart()::ncclResult_t
 end
 
-# no prototype is found for this function at nccl.h:417:14, please use with caution
+# no prototype is found for this function at nccl.h:547:14, please use with caution
 @checked function pncclGroupStart()
     @ccall libnccl.pncclGroupStart()::ncclResult_t
 end
 
-# no prototype is found for this function at nccl.h:426:15, please use with caution
+# no prototype is found for this function at nccl.h:556:15, please use with caution
 @checked function ncclGroupEnd()
     @ccall libnccl.ncclGroupEnd()::ncclResult_t
 end
 
-# no prototype is found for this function at nccl.h:427:14, please use with caution
+# no prototype is found for this function at nccl.h:557:14, please use with caution
 @checked function pncclGroupEnd()
     @ccall libnccl.pncclGroupEnd()::ncclResult_t
 end
 
-@checked function ncclCommRegister(comm, buff, size, handle)
-    @ccall libnccl.ncclCommRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
-                                    handle::Ptr{Ptr{Cvoid}})::ncclResult_t
+@checked function ncclGroupSimulateEnd(simInfo)
+    @ccall libnccl.ncclGroupSimulateEnd(simInfo::Ptr{ncclSimInfo_t})::ncclResult_t
 end
 
-@checked function pncclCommRegister(comm, buff, size, handle)
-    @ccall libnccl.pncclCommRegister(comm::ncclComm_t, buff::CuPtr{Cvoid}, size::Cint,
-                                     handle::Ptr{Ptr{Cvoid}})::ncclResult_t
-end
-
-@checked function ncclCommDeregister(comm, handle)
-    @ccall libnccl.ncclCommDeregister(comm::ncclComm_t, handle::CuPtr{Cvoid})::ncclResult_t
-end
-
-@checked function pncclCommDeregister(comm, handle)
-    @ccall libnccl.pncclCommDeregister(comm::ncclComm_t, handle::CuPtr{Cvoid})::ncclResult_t
+@checked function pncclGroupSimulateEnd(simInfo)
+    @ccall libnccl.pncclGroupSimulateEnd(simInfo::Ptr{ncclSimInfo_t})::ncclResult_t
 end
 
 const NCCL_MAJOR = 2
 
-const NCCL_MINOR = 19
+const NCCL_MINOR = 28
 
-const NCCL_PATCH = 4
+const NCCL_PATCH = 3
 
 const NCCL_SUFFIX = ""
 
-const NCCL_VERSION_CODE = 21904
+const NCCL_VERSION_CODE = 22803
 
 const NCCL_COMM_NULL = NULL
 
@@ -413,7 +543,28 @@ const NCCL_CONFIG_UNDEF_PTR = NULL
 
 const NCCL_SPLIT_NOCOLOR = -1
 
-# Skipping MacroDefinition: NCCL_CONFIG_INITIALIZER { sizeof ( ncclConfig_t ) , /* size */ 0xcafebeef , /* magic */ NCCL_VERSION ( NCCL_MAJOR , NCCL_MINOR , NCCL_PATCH ) , /* version */ NCCL_CONFIG_UNDEF_INT , /* blocking */ NCCL_CONFIG_UNDEF_INT , /* cgaClusterSize */ NCCL_CONFIG_UNDEF_INT , /* minCTAs */ NCCL_CONFIG_UNDEF_INT , /* maxCTAs */ NCCL_CONFIG_UNDEF_PTR , /* netName */ NCCL_CONFIG_UNDEF_INT /* splitShare */ \
+const NCCL_UNDEF_FLOAT = -(Float32(1.0))
+
+const NCCL_WIN_DEFAULT = 0x00
+
+const NCCL_WIN_COLL_SYMMETRIC = 0x01
+
+const NCCL_WIN_REQUIRED_ALIGNMENT = 4096
+
+const NCCL_CTA_POLICY_DEFAULT = 0x00
+
+const NCCL_CTA_POLICY_EFFICIENCY = 0x01
+
+const NCCL_CTA_POLICY_ZERO = 0x02
+
+const NCCL_SHRINK_DEFAULT = 0x00
+
+const NCCL_SHRINK_ABORT = 0x01
+
+# Skipping MacroDefinition: NCCL_CONFIG_INITIALIZER { sizeof ( ncclConfig_t ) , /* size */ 0xcafebeef , /* magic */ NCCL_VERSION ( NCCL_MAJOR , NCCL_MINOR , NCCL_PATCH ) , /* version */ NCCL_CONFIG_UNDEF_INT , /* blocking */ NCCL_CONFIG_UNDEF_INT , /* cgaClusterSize */ NCCL_CONFIG_UNDEF_INT , /* minCTAs */ NCCL_CONFIG_UNDEF_INT , /* maxCTAs */ NCCL_CONFIG_UNDEF_PTR , /* netName */ NCCL_CONFIG_UNDEF_INT , /* splitShare */ NCCL_CONFIG_UNDEF_INT , /* trafficClass */ NCCL_CONFIG_UNDEF_PTR , /* commName */ NCCL_CONFIG_UNDEF_INT , /* collnetEnable */ NCCL_CONFIG_UNDEF_INT , /* CTAPolicy */ NCCL_CONFIG_UNDEF_INT , /* shrinkShare */ NCCL_CONFIG_UNDEF_INT , /* nvlsCTAs */ NCCL_CONFIG_UNDEF_INT , /* nChannelsPerNetPeer */ NCCL_CONFIG_UNDEF_INT , /* nvlinkCentricSched */ \
+#}
+
+# Skipping MacroDefinition: NCCL_SIM_INFO_INITIALIZER { sizeof ( ncclSimInfo_t ) , /* size */ 0x74685283 , /* magic */ NCCL_VERSION ( NCCL_MAJOR , NCCL_MINOR , NCCL_PATCH ) , /* version */ NCCL_UNDEF_FLOAT /* estimated time */ \
 #}
 
 export NCCLError
diff --git a/test/Project.toml b/test/Project.toml
index 73f75fc..0b76d47 100644
--- a/test/Project.toml
+++ b/test/Project.toml
@@ -1,3 +1,4 @@
 [deps]
+NCCL_jll = "4d6d38e4-5b87-5e63-912a-873ff2d649b7"
 CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
diff --git a/test/runtests.jl b/test/runtests.jl
index df695c0..223313e 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -3,6 +3,11 @@ using Test
 using CUDA
 @info "CUDA information:\n" * sprint(io->CUDA.versioninfo(io))
 
+using NCCL_jll
+@info "host_platform: $(NCCL_jll.host_platform)"
+@info "is_available: $(NCCL_jll.is_available())"
+@info "best_wrapper: $(NCCL_jll.best_wrapper)"
+
 using NCCL
 @info "NCCL version: $(NCCL.version())"