Remove Tracker and replace with Mooncake, except in BNN doc

penelopeysm · penelopeysm · commit aca574f427fd · 2024-11-25T19:02:08.000Z
diff --git a/Manifest.toml b/Manifest.toml
@@ -2,7 +2,7 @@
 
 julia_version = "1.10.6"
 manifest_format = "2.0"
-project_hash = "d445da060c06170cbd2a3f76f676702d3ccabd6c"
+project_hash = "46b1a3e94b0848456d070eb24006f64ff234812a"
 
 [[deps.ADTypes]]
 git-tree-sha1 = "72af59f5b8f09faee36b4ec48e014a79210f2f4f"
@@ -702,6 +702,12 @@ git-tree-sha1 = "23163d55f885173722d1e4cf0f6110cdbaf7e272"
 uuid = "b552c78f-8df3-52c6-915a-8e097449b14b"
 version = "1.15.1"
 
+[[deps.DiffTests]]
+deps = ["LinearAlgebra", "SparseArrays", "Statistics"]
+git-tree-sha1 = "b92beb1933df01bf4915d3a05e54c2a0aad312c7"
+uuid = "de460e47-3fe3-5279-bb4a-814414816d5d"
+version = "0.1.2"
+
 [[deps.DifferentialEquations]]
 deps = ["BoundaryValueDiffEq", "DelayDiffEq", "DiffEqBase", "DiffEqCallbacks", "DiffEqNoiseProcess", "JumpProcesses", "LinearAlgebra", "LinearSolve", "NonlinearSolve", "OrdinaryDiffEq", "Random", "RecursiveArrayTools", "Reexport", "SciMLBase", "SteadyStateDiffEq", "StochasticDiffEq", "Sundials"]
 git-tree-sha1 = "d55af9d6b51c54f81ae30d1a463206d32cc4c24a"
@@ -2103,6 +2109,11 @@ git-tree-sha1 = "ec4f7fbeab05d7747bdf98eb74d130a2a2ed298d"
 uuid = "e1d29d7a-bbdc-5cf2-9ac0-f12de2c33e28"
 version = "1.2.0"
 
+[[deps.MistyClosures]]
+git-tree-sha1 = "1142aefd845c608f3c70e4c202c4aae725cab67b"
+uuid = "dbe65cb8-6be2-42dd-bbc5-4196aaced4f4"
+version = "2.0.0"
+
 [[deps.Mmap]]
 uuid = "a63ad114-7e13-5084-954f-fe012c677804"
 
@@ -2112,6 +2123,32 @@ git-tree-sha1 = "2c140d60d7cb82badf06d8783800d0bcd1a7daa2"
 uuid = "78c3b35d-d492-501b-9361-3d52fe80e533"
 version = "0.8.1"
 
+[[deps.Mooncake]]
+deps = ["ADTypes", "ChainRules", "ChainRulesCore", "DiffRules", "DiffTests", "ExprTools", "FunctionWrappers", "Graphs", "InteractiveUtils", "LinearAlgebra", "MistyClosures", "Random", "Setfield", "Test"]
+git-tree-sha1 = "9fa3c8c11fe5286badb9c24e8d2420b3a07f9a8c"
+uuid = "da2b9cff-9c12-43a0-ae48-6db2b0edb7d6"
+version = "0.4.50"
+
+    [deps.Mooncake.extensions]
+    MooncakeAllocCheckExt = "AllocCheck"
+    MooncakeCUDAExt = "CUDA"
+    MooncakeDynamicPPLExt = "DynamicPPL"
+    MooncakeJETExt = "JET"
+    MooncakeLuxLibExt = "LuxLib"
+    MooncakeLuxLibSLEEFPiratesExtension = ["LuxLib", "SLEEFPirates"]
+    MooncakeNNlibExt = "NNlib"
+    MooncakeSpecialFunctionsExt = "SpecialFunctions"
+
+    [deps.Mooncake.weakdeps]
+    AllocCheck = "9b6a8646-10ed-4001-bbdc-1d2f46dfbb1a"
+    CUDA = "052768ef-5323-5732-b1bb-66c8b64840ba"
+    DynamicPPL = "366bfd00-2699-11ea-058f-f148b4cae6d8"
+    JET = "c3a54625-cd67-489e-a8e7-0a5a0ff4e31b"
+    LuxLib = "82251201-b29d-42c6-8e01-566dec8acb11"
+    NNlib = "872c559c-99b0-510c-b3b7-b6c96a88d5cd"
+    SLEEFPirates = "476501e8-09a2-5ece-8869-fb82de89a1fa"
+    SpecialFunctions = "276daf66-3868-5448-9aa4-cd146d93841b"
+
 [[deps.MozillaCACerts_jll]]
 uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
 version = "2023.1.10"
diff --git a/Project.toml b/Project.toml
@@ -33,6 +33,7 @@ MacroTools = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
 Measures = "442fdcdd-2543-5da2-b0f3-8c86c306513e"
 Memoization = "6fafb56a-5788-4b4e-91ca-c0cea6611c73"
 MicroCanonicalHMC = "234d2aa0-2291-45f7-9047-6fa6f316b0a8"
+Mooncake = "da2b9cff-9c12-43a0-ae48-6db2b0edb7d6"
 NNlib = "872c559c-99b0-510c-b3b7-b6c96a88d5cd"
 Optimization = "7f7a1694-90dd-40f0-9382-eb1efda571ba"
 OptimizationNLopt = "4e6fcdb7-1186-4e1f-a706-475e75c168bb"
@@ -48,7 +49,6 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 StatsFuns = "4c63d2b9-4356-54db-8cca-17b64c39e42c"
 StatsPlots = "f3b207a7-027a-5e70-b257-86293d7955fd"
-Tracker = "9f7883ad-71c0-57eb-9f7f-b5c9e6d3789c"
 Turing = "fce5fe82-541a-59a6-adf8-730c64b5f9a0"
 UnPack = "3a884ed6-31ef-47d7-9d2a-63182c4928ed"
 Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
diff --git a/tutorials/10-bayesian-differential-equations/index.qmd b/tutorials/10-bayesian-differential-equations/index.qmd
@@ -320,7 +320,7 @@ More theoretical details on these methods can be found at: https://docs.sciml.ai
 While these sensitivity analysis methods may seem complicated, using them is dead simple.
 Here is a version of the Lotka-Volterra model using adjoint sensitivities.
 
-All we have to do is switch the AD backend to one of the adjoint-compatible backends (ReverseDiff, Tracker, or Zygote)!
+All we have to do is switch the AD backend to one of the adjoint-compatible backends (ReverseDiff or Zygote)!
 Notice that on this model adjoints are slower.
 This is because adjoints have a higher overhead on small parameter models and therefore we suggest using these methods only for models with around 100 parameters or more.
 For more details, see https://arxiv.org/abs/1812.01892.
diff --git a/tutorials/docs-10-using-turing-autodiff/index.qmd b/tutorials/docs-10-using-turing-autodiff/index.qmd
@@ -12,9 +12,8 @@ Pkg.instantiate();
 
 ## Switching AD Modes
 
-Turing currently supports four automatic differentiation (AD) backends for sampling: [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) for forward-mode AD; and [ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl), [Zygote](https://github.com/FluxML/Zygote.jl), and [Tracker](https://github.com/FluxML/Tracker.jl) for reverse-mode AD.
-While `Tracker` is still available, its use is discouraged due to a lack of active maintenance.
-`ForwardDiff` is automatically imported by Turing. To utilize `Zygote` or `ReverseDiff` for AD, users must explicitly import them with `using Zygote` or `using ReverseDiff`, alongside `using Turing`.
+Turing currently supports four automatic differentiation (AD) backends for sampling: [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) for forward-mode AD; and [Mooncake](https://github.com/compintell/Mooncake.jl), [ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl), and [Zygote](https://github.com/FluxML/Zygote.jl) for reverse-mode AD.
+`ForwardDiff` is automatically imported by Turing. To utilize `Mooncake`, `Zygote`, or `ReverseDiff` for AD, users must explicitly import them with `import Mooncake`, `import Zygote` or `import ReverseDiff`, alongside `using Turing`.
 
 As of Turing version v0.30, the global configuration flag for the AD backend has been removed in favour of [`AdTypes.jl`](https://github.com/SciML/ADTypes.jl), allowing users to specify the AD backend for individual samplers independently.
 Users can pass the `adtype` keyword argument to the sampler constructor to select the desired AD backend, with the default being `AutoForwardDiff(; chunksize=0)`.
@@ -62,4 +61,4 @@ c = sample(
 
 Generally, reverse-mode AD, for instance `ReverseDiff`, is faster when sampling from variables of high dimensionality (greater than 20), while forward-mode AD, for instance `ForwardDiff`, is more efficient for lower-dimension variables. This functionality allows those who are performance sensitive to fine tune their automatic differentiation for their specific models.
 
-If the differentiation method is not specified in this way, Turing will default to using whatever the global AD backend is. Currently, this defaults to `ForwardDiff`.
+If the differentiation method is not specified in this way, Turing will default to using whatever the global AD backend is. Currently, this defaults to `ForwardDiff`.
diff --git a/tutorials/docs-12-using-turing-guide/index.qmd b/tutorials/docs-12-using-turing-guide/index.qmd
@@ -514,7 +514,7 @@ ForwardDiff (Turing's default AD backend) uses forward-mode chunk-wise AD. The c
 
 #### AD Backend
 
-Turing supports four automatic differentiation (AD) packages in the back end during sampling. The default AD backend is [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) for forward-mode AD. Three reverse-mode AD backends are also supported, namely [Tracker](https://github.com/FluxML/Tracker.jl), [Zygote](https://github.com/FluxML/Zygote.jl) and [ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl). `Zygote` and `ReverseDiff` are supported optionally if explicitly loaded by the user with `using Zygote` or `using ReverseDiff` next to `using Turing`.
+Turing supports four automatic differentiation (AD) packages in the back end during sampling. The default AD backend is [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) for forward-mode AD. Three reverse-mode AD backends are also supported, namely [Mooncake](https://github.com/compintell/Mooncake.jl), [Zygote](https://github.com/FluxML/Zygote.jl) and [ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl). `Mooncake`, `Zygote`, and `ReverseDiff` also require the user to explicitly load them using `import Mooncake`, `import Zygote`, or `import ReverseDiff` next to `using Turing`.
 
 For more information on Turing's automatic differentiation backend, please see the [Automatic Differentiation]({{<meta using-turing-autodiff>}}) article.
 
diff --git a/tutorials/docs-13-using-turing-performance-tips/index.qmd b/tutorials/docs-13-using-turing-performance-tips/index.qmd
@@ -43,19 +43,20 @@ end
 ## Choose your AD backend
 
 Automatic differentiation (AD) makes it possible to use modern, efficient gradient-based samplers like NUTS and HMC, and that means a good AD system is incredibly important. Turing currently
-supports several AD backends, including [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) (the default), [Zygote](https://github.com/FluxML/Zygote.jl),
-[ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl), and [Tracker](https://github.com/FluxML/Tracker.jl). Experimental support is also available for
-[Tapir](https://github.com/withbayes/Tapir.jl).
+supports several AD backends, including [ForwardDiff](https://github.com/JuliaDiff/ForwardDiff.jl) (the default),
+[Mooncake](https://github.com/compintell/Mooncake.jl),
+[Zygote](https://github.com/FluxML/Zygote.jl), and
+[ReverseDiff](https://github.com/JuliaDiff/ReverseDiff.jl).
 
 For many common types of models, the default ForwardDiff backend performs great, and there is no need to worry about changing it. However, if you need more speed, you can try
 different backends via the standard [ADTypes](https://github.com/SciML/ADTypes.jl) interface by passing an `AbstractADType` to the sampler with the optional `adtype` argument, e.g.
 `NUTS(adtype = AutoZygote())`. See [Automatic Differentiation]({{<meta using-turing-autodiff>}}) for details. Generally, `adtype = AutoForwardDiff()` is likely to be the fastest and most reliable for models with
 few parameters (say, less than 20 or so), while reverse-mode backends such as `AutoZygote()` or `AutoReverseDiff()` will perform better for models with many parameters or linear algebra
 operations. If in doubt, it's easy to try a few different backends to see how they compare.
 
-### Special care for Zygote and Tracker
+### Special care for Zygote
 
-Note that Zygote and Tracker will not perform well if your model contains `for`-loops, due to the way reverse-mode AD is implemented in these packages. Zygote also cannot differentiate code
+Note that Zygote will not perform well if your model contains `for`-loops, due to the way reverse-mode AD is implemented in these packages. Zygote also cannot differentiate code
 that contains mutating operations. If you can't implement your model without `for`-loops or mutation, `ReverseDiff` will be a better, more performant option. In general, though,
 vectorized operations are still likely to perform best.
 
