• Improved the embedded Laplace approximation. (#3250, #3286, #3297, #3281)
• Added yule_simon_lcdf, yule_simon_cdf, and yule_simon_rng. (#3276, #3283, #3285)
• Added quantile function for student-t distribution. (#3211)
• Added trace_dot(A, B). (#3310)
• Improved the robustness of gamma_lccdf. (#3275, #3272, #3292, #3296)
• Set thread QoS to USER_INITIATED on Apple Silicon. (#3278)
• Updated tests to ensure they properly clean up memory. (#3293)
• Fixed typos in error messages, code comments. (#3295)
• Documented parameter 'y' in apply_scalar_binary. (#3284)
• Jenkins: change how gh-pages branch gets re-built. (#3316)
• Jenkins: improved error handling of parallel distribution tests. (#3307)
• Updated OpenCL C++ to use v2025.07.22. (#3298)
• Updated cpplint to 2.0.2. (#3294)

• Added the unnormalized CDF and CCDF for the wiener 7-parameter diffusion model. Allows modeling truncated and censored data. (#3042, #3258, #3260, #3263)

• Added yule_simon_lpmf and yule_simon_lccdf. Allows modeling power-law count data. (#3220, #3236)

• Updated wording of validate_positive_index. (#3248)

• Replaced standard if statements with if constexpr where posssible. (#3240)

• Removed use of forward_as in the math library. (#3242)

• Added some more type traits for dealing with tuples. (#3244)

• Added inline to all functions. (#3245)

• Added functions for the embedded Laplace approximation. (#3097, #3209, #3210)
• Added new overloads for sum_to_zero_constrain and sum_to_zero_free that accept Eigen Matrix types. (#3169)
• The simplex transform is now defined in terms of the isometric log ratio transform instead of stick breaking. (#3171)
• Renamed hypergeometric_1f0 to hypergeometric_1F0 for consistency, fixed compilation for hypergeometric_2f1 with autodiff second argument. (#3165)
• Simplified implementation of chol2inv using matrix functions. (#3136)
• Improved the numerical stability of the gradient calculations for inv_Phi and std_normal_log_qf. (#3139, #3207)
• Simplified vectorisation of std_normal_lpdf. (#3140)
• Removed redundant computation in grad_reg_inc_beta. (#3159)
• Updated signature for apply_scalar_binary to take the functor as its first argument, instead of the last. (#3156)
• Added perfect forwarding to all functions that use the apply_ family of functors. (#3221, #3228, #3229)
• Fixed expression test errors with poisson_binomial_rng, added support for row-vector and std::vector<double> theta arguments for poisson_binomial. (#3178)
• Updated inv_logit to use the logistic function from Eigen. (#3155, #3160)
• Update the constraint functions templating to be more flexible. (#3151)
• Added ARM64 testing to the Github CI for Windows and Ubuntu (#3177, #3173, #3180, #3174, #3158, #3164)
• Disabled Make's implicit rules in our Makefiles. (#3183)
• Updated Boost to version 1.87.0 (#3185)
• Patched an issue preventing TBB from building with clang 21.1 (#3223)

Breaking changes:

• Removed deprecated _log() probability functions. (#2995)
• Moved constraint transforms to their own folder. (#3039)
• Updated arena_matrix to use move semantics. (#2928)
• Un-vendored a great many unused boost libraries. (#3129)
• C++17 is now required.

Other changes:

• Added sum_to_zero_constrain, sum_to_zero_free, and check_sum_to_zero. (#3101)
• Added beta_neg_binomial_lpmf. Allows modeling heavy-tail count data. (#3108)
• Added beta_neg_binomial_lccdf. (#3114, #3118)
• Added beta_neg_binomial_lcdf. (#3116)
• Added beta_neg_binomial_cdf. (#3120)
• Added beta_neg_binomial_rng. (#3126)
• Added overloads for tuples of bounds to lub_free and lub_constrain. (#3087)
• Added error checking functions for row/column stochastic matrices. (#3095)
• Added constructor to vari for passing initial values and adjoints. (#3089)
• Improved efficiency of finite_diff_gradient_auto. (#3096)
• Functions concerned with the number of entries in a container (size, cols, rows, ...) now consistently use long int as their return type. (#3086)
• Removed support for adding makefile variables in ~/.config/stan/make.local. Use the make/local file in the Math directory instead. (#3090)
• Fixed an indexing bug inside gp_matern32_cov. (#3084)
• Fixed the new wiener_lpdf overloads evaluating their expression template arguments more than once. (#3112)
• Fixed some failures to compile calls to pow when using libc++ 19. (#3110)
• Updated templated complex functions in the Stan math library to be better candidates than the standard library functions during ADL. (#3122)
• Fixed a warning about a mismatched struct/class declaration from clang 18. (#3091)
• Fixed compilation of fabs with Apple Clang 15. (#3093)
• Fix Eigen issue 2852 so that Eigen's kronecker product type works with value_type_t. (#3124)