Add tests for var_value<Matrix> for univariate distributions #2304

SteveBronder · 2021-01-11T17:51:28Z

Summary

This modifies the distribution test suite so that var_value<Matrix> is also tested.

Tests

All the standard distribution tests but using var_value<Matrix>

Side Effects

Nope

Release notes

Tests distributions are var_value<Matrix> compatible

Checklist

Math issue How to add static matrix? #1805
Copyright holder: Steve Bronder

The copyright holder is typically you or your assignee, such as a university or company. By submitting this pull request, the copyright holder is agreeing to the license the submitted work under the following licenses:
- Code: BSD 3-clause (https://opensource.org/licenses/BSD-3-Clause)
- Documentation: CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/)
the basic tests are passing
- unit tests pass (to run, use: ./runTests.py test/unit)
- header checks pass, (make test-headers)
- dependencies checks pass, (make test-math-dependencies)
- docs build, (make doxygen)
- code passes the built in C++ standards checks (make cpplint)
the code is written in idiomatic C++ and changes are documented in the doxygen
the new changes are tested

…4.1 (tags/RELEASE_600/final)

bbbales2

Took a skim. There were some value_ofs on stuff that I think are integers

bbbales2 · 2021-01-12T00:04:41Z

stan/math/prim/prob/poisson_binomial_lcdf.hpp

-    check_finite(function, "Probability parameters", theta_vec[i]);
-    check_bounded(function, "Probability parameters", theta_vec[i], 0.0, 1.0);
+    check_finite(function, "Probability parameters", value_of(theta_vec[i]));
+    check_bounded(function, "Probability parameters", value_of(theta_vec[i]), 0.0, 1.0);


theta_vec.val(i)

bbbales2 · 2021-01-12T00:04:51Z

stan/math/prim/prob/poisson_binomial_lpmf.hpp

@@ -43,7 +43,7 @@ return_type_t<T_theta> poisson_binomial_lpmf(const T_y& y,
    check_bounded(function, "Successes variable", y_vec[i], 0,
                  theta_vec[i].size());
    check_finite(function, "Probability parameters", theta_vec[i]);
-    check_bounded(function, "Probability parameters", theta_vec[i], 0.0, 1.0);
+    check_bounded(function, "Probability parameters", value_of(theta_vec[i]), 0.0, 1.0);


theta_vec.val(i)

stan/math/prim/prob/bernoulli_logit_glm_lpmf.hpp

bbbales2 · 2021-01-12T00:06:56Z

stan/math/prim/prob/bernoulli_logit_lpmf.hpp

@@ -47,7 +47,7 @@ return_type_t<T_prob> bernoulli_logit_lpmf(const T_n& n, const T_prob& theta) {
  }
  T_n_ref n_ref = n;
  T_theta_ref theta_ref = theta;
-  check_bounded(function, "n", n_ref, 0, 1);
+  check_bounded(function, "n", value_of(n_ref), 0, 1);


Integer, value_of not necessary

Is it guaranteed somewhere to always be an integer or do we only check that at the Stan language level?

Stan language. These are the signatures:

real bernoulli_logit_lpmf(int, real) real bernoulli_logit_lpmf(int, vector) real bernoulli_logit_lpmf(int, row_vector) real bernoulli_logit_lpmf(int, real[]) real bernoulli_logit_lpmf(int[], real) real bernoulli_logit_lpmf(int[], vector) real bernoulli_logit_lpmf(int[], row_vector) real bernoulli_logit_lpmf(int[], real[])

(from: bin/stanc --dump-stan-math-signatures | grep bernoulli_logit_lpmf)

idk, idt there's anything bad about calling value_of here. Idt it would be an error and I don't think it would be a performance thing

bbbales2 · 2021-01-12T00:07:49Z

stan/math/prim/prob/bernoulli_lpmf.hpp

@@ -41,8 +41,9 @@ return_type_t<T_prob> bernoulli_lpmf(const T_n& n, const T_prob& theta) {
                         "Probability parameter", theta);
  const T_n_ref n_ref = to_ref(n);
  const T_theta_ref theta_ref = to_ref(theta);
-  check_bounded(function, "n", n_ref, 0, 1);
-  check_bounded(function, "Probability parameter", theta_ref, 0.0, 1.0);
+  check_bounded(function, "n", value_of(n_ref), 0, 1);


Integer, value_of not necessary

bbbales2 · 2021-01-12T00:10:35Z

stan/math/prim/prob/hypergeometric_rng.hpp

@@ -15,7 +15,7 @@ inline int hypergeometric_rng(int N, int a, int b, RNG& rng) {
  using boost::variate_generator;
  using boost::math::hypergeometric_distribution;
  static const char* function = "hypergeometric_rng";
-  check_bounded(function, "Draws parameter", N, 0, a + b);
+  check_bounded(function, "Draws parameter", value_of(N), 0, a + b);


bbbales2 · 2021-01-12T00:11:12Z

stan/math/prim/prob/ordered_logistic_glm_lpmf.hpp

@@ -74,7 +74,8 @@ return_type_t<T_x, T_beta, T_cuts> ordered_logistic_glm_lpmf(
  T_cuts_ref cuts_ref = cuts;
  const auto& cuts_val = value_of_rec(cuts_ref);
  const auto& cuts_val_vec = to_ref(as_column_vector_or_scalar(cuts_val));
-  check_bounded(function, "Vector of dependent variables", y_ref, 1, N_classes);
+  check_bounded(function, "Vector of dependent variables", value_of(y_ref), 1,


bbbales2 · 2021-01-12T00:11:21Z

stan/math/prim/prob/ordered_logistic_lpmf.hpp

@@ -103,7 +103,7 @@ return_type_t<T_loc, T_cut> ordered_logistic_lpmf(const T_y& y,
  const auto& lambda_arr = as_array_or_scalar(lambda_ref);
  ref_type_t<decltype(value_of(lambda_arr))> lambda_val = value_of(lambda_arr);

-  check_bounded(function, "Random variable", y_ref, 1, K);
+  check_bounded(function, "Random variable", value_of(y_ref), 1, K);


stan/math/prim/prob/poisson_binomial_lcdf.hpp

bbbales2 · 2021-01-12T00:11:57Z

stan/math/prim/prob/poisson_binomial_lpmf.hpp

@@ -43,7 +43,8 @@ return_type_t<T_theta> poisson_binomial_lpmf(const T_y& y,
    check_bounded(function, "Successes variable", y_vec[i], 0,
                  theta_vec[i].size());
    check_finite(function, "Probability parameters", theta_vec[i]);
-    check_bounded(function, "Probability parameters", theta_vec[i], 0.0, 1.0);
+    check_bounded(function, "Probability parameters", value_of(theta_vec[i]),


theta_vec.val(i)

…4.1 (tags/RELEASE_600/final)

…into feature/varmat-dist-tests

…s lpdf (Issue #2101)

bbbales2 · 2021-01-12T22:55:45Z

stan/math/prim/prob/von_mises_lpdf.hpp

-    const auto& bessel1 = modified_bessel_first_kind(-1, kappa_val);
-    ops_partials.edge3_.partials_ = cos_mu_minus_y - bessel1 / bessel0;
+    ops_partials.edge3_.partials_ = cos_mu_minus_y -
+      modified_bessel_first_kind(-1, kappa_val) / modified_bessel_first_kind(0, kappa_val);


If I didn't* do this inline, I was getting memory problems with expressions.

Edit: did -> didn't*

…4.1 (tags/RELEASE_600/final)

…2101)

)

…into feature/varmat-dist-tests

…4.1 (tags/RELEASE_600/final)

stan-buildbot · 2021-01-14T01:10:14Z

Name	Old Result	New Result	Ratio	Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan	3.42	3.37	1.01	1.36% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan	0.02	0.02	0.98	-2.23% slower
eight_schools/eight_schools.stan	0.11	0.12	0.94	-6.86% slower
gp_regr/gp_regr.stan	0.15	0.15	1.02	1.91% faster
irt_2pl/irt_2pl.stan	5.2	5.14	1.01	1.2% faster
performance.compilation	91.57	89.63	1.02	2.11% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan	8.64	8.65	1.0	-0.14% slower
pkpd/one_comp_mm_elim_abs.stan	29.2	27.81	1.05	4.74% faster
sir/sir.stan	137.49	135.43	1.02	1.49% faster
gp_regr/gen_gp_data.stan	0.04	0.04	0.99	-0.6% slower
low_dim_gauss_mix/low_dim_gauss_mix.stan	3.04	3.05	1.0	-0.25% slower
pkpd/sim_one_comp_mm_elim_abs.stan	0.38	0.4	0.95	-5.25% slower
arK/arK.stan	2.56	2.54	1.01	0.73% faster
arma/arma.stan	0.61	0.62	0.98	-2.56% slower
garch/garch.stan	0.57	0.57	0.99	-0.55% slower
Mean result: 0.997532618535

Jenkins Console Log
Blue Ocean
Commit hash: dd3f0f8

Machine information

ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

bbbales2 · 2021-01-14T02:16:48Z

Greencheck woooo. We got time to polish this a bit more since we aren't trying to merge varmats this release now.

…t-tests

SteveBronder · 2021-01-26T20:53:13Z

stan/math/prim/prob/bernoulli_lpmf.hpp

@@ -68,12 +69,12 @@ return_type_t<T_prob> bernoulli_lpmf(const T_n& n, const T_prob& theta) {
    if (sum == N) {
      logp += N * log(theta_dbl);
      if (!is_constant_all<T_prob>::value) {
-        ops_partials.edge1_.partials_[0] += N / theta_dbl;
+        ops_partials.edge1_.partials_[0] += N * inv(theta_dbl);


What's up with this change?

Oh this happened in a few places, why switch from / to * inv()?

I'm gonna add the static cast to double for the division here inf fvar's divide

test/prob/gamma/gamma_ccdf_log_test.hpp

stan-buildbot · 2021-01-27T03:09:25Z

Name	Old Result	New Result	Ratio	Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan	3.53	3.45	1.02	2.17% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan	0.02	0.02	1.03	3.31% faster
eight_schools/eight_schools.stan	0.12	0.11	1.06	5.59% faster
gp_regr/gp_regr.stan	0.15	0.15	1.0	-0.29% slower
irt_2pl/irt_2pl.stan	5.22	5.26	0.99	-0.83% slower
performance.compilation	92.11	90.13	1.02	2.15% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan	8.75	8.66	1.01	1.01% faster
pkpd/one_comp_mm_elim_abs.stan	29.09	29.93	0.97	-2.87% slower
sir/sir.stan	130.85	125.2	1.05	4.32% faster
gp_regr/gen_gp_data.stan	0.04	0.04	0.98	-1.78% slower
low_dim_gauss_mix/low_dim_gauss_mix.stan	3.13	3.08	1.02	1.59% faster
pkpd/sim_one_comp_mm_elim_abs.stan	0.4	0.41	0.98	-1.85% slower
arK/arK.stan	1.85	1.85	1.0	-0.07% slower
arma/arma.stan	0.62	0.6	1.03	2.5% faster
garch/garch.stan	0.59	0.6	0.99	-0.9% slower
Mean result: 1.01002559519

Jenkins Console Log
Blue Ocean
Commit hash: 034d009

Machine information

ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

…t-tests

…4.1 (tags/RELEASE_600/final)

SteveBronder · 2021-01-31T00:30:55Z

Alright I think with the division thing all that's left to do is sort out the integer value of and we are good. Personally idt it hurts and from the math library it is possible to have a var there

bbbales2 · 2021-02-01T15:03:36Z

I cleaned out the test changes that didn't need to change and removed the value_ofs (gradients aren't going to work even if we do value_of if someone passes in a var). This pull is all good to me.

…4.1 (tags/RELEASE_600/final)

…t-tests

…into feature/varmat-dist-tests

SteveBronder · 2021-02-01T19:56:21Z

All good to me as well! though idt I can approve because I'm the author

stan-buildbot · 2021-02-02T07:28:30Z

Name	Old Result	New Result	Ratio	Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan	3.45	3.41	1.01	1.26% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan	0.02	0.02	1.02	1.98% faster
eight_schools/eight_schools.stan	0.11	0.11	0.99	-0.81% slower
gp_regr/gp_regr.stan	0.16	0.15	1.01	1.32% faster
irt_2pl/irt_2pl.stan	5.18	5.36	0.97	-3.46% slower
performance.compilation	92.74	90.17	1.03	2.78% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan	8.65	8.65	1.0	0.05% faster
pkpd/one_comp_mm_elim_abs.stan	28.28	29.23	0.97	-3.36% slower
sir/sir.stan	123.35	125.13	0.99	-1.44% slower
gp_regr/gen_gp_data.stan	0.04	0.04	1.0	0.24% faster
low_dim_gauss_mix/low_dim_gauss_mix.stan	3.13	3.05	1.03	2.53% faster
pkpd/sim_one_comp_mm_elim_abs.stan	0.37	0.38	0.98	-2.39% slower
arK/arK.stan	1.84	1.85	0.99	-0.85% slower
arma/arma.stan	0.6	0.6	1.0	0.21% faster
garch/garch.stan	0.59	0.59	1.0	0.17% faster
Mean result: 0.999180163139

Jenkins Console Log
Blue Ocean
Commit hash: 46e49f8

Machine information

ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

…t-tests

stan-buildbot · 2021-02-04T15:02:35Z

Name	Old Result	New Result	Ratio	Performance change( 1 - new / old )
gp_pois_regr/gp_pois_regr.stan	3.49	3.39	1.03	2.71% faster
low_dim_corr_gauss/low_dim_corr_gauss.stan	0.02	0.02	0.98	-1.94% slower
eight_schools/eight_schools.stan	0.11	0.11	0.98	-2.47% slower
gp_regr/gp_regr.stan	0.15	0.15	0.98	-2.4% slower
irt_2pl/irt_2pl.stan	5.2	5.21	1.0	-0.32% slower
performance.compilation	91.43	88.31	1.04	3.41% faster
low_dim_gauss_mix_collapse/low_dim_gauss_mix_collapse.stan	8.64	8.73	0.99	-1.04% slower
pkpd/one_comp_mm_elim_abs.stan	29.64	29.09	1.02	1.87% faster
sir/sir.stan	133.52	140.26	0.95	-5.05% slower
gp_regr/gen_gp_data.stan	0.04	0.05	0.92	-8.6% slower
low_dim_gauss_mix/low_dim_gauss_mix.stan	3.09	3.05	1.01	1.23% faster
pkpd/sim_one_comp_mm_elim_abs.stan	0.4	0.38	1.05	5.07% faster
arK/arK.stan	2.55	2.55	1.0	0.22% faster
arma/arma.stan	0.61	0.61	1.0	0.03% faster
garch/garch.stan	0.53	0.53	0.99	-0.81% slower
Mean result: 0.995681017563

Jenkins Console Log
Blue Ocean
Commit hash: 57d4438

Machine information

ProductName: Mac OS X ProductVersion: 10.11.6 BuildVersion: 15G22010

CPU:
Intel(R) Xeon(R) CPU E5-1680 v2 @ 3.00GHz

G++:
Configured with: --prefix=/Applications/Xcode.app/Contents/Developer/usr --with-gxx-include-dir=/usr/include/c++/4.2.1
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

Clang:
Apple LLVM version 7.0.2 (clang-700.1.81)
Target: x86_64-apple-darwin15.6.0
Thread model: posix

SteveBronder and others added 4 commits January 11, 2021 10:49

adds tests for var_value<Matrix> to distributions

e99e1f8

fix tests makefile

3a92428

checks value_of() for error handling in distributions

e625777

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

d0c2d4b

…4.1 (tags/RELEASE_600/final)

bbbales2 requested changes Jan 12, 2021

View reviewed changes

bbbales2 and others added 9 commits January 12, 2021 08:23

Added value_of to beta proportion lcdf and lccdf (Issue #2101)

5eae85c

Updated VectorBuilder to work with varmat (Issue #2101)

e7dc4b3

Fixed is_vector check in VectorBuilder (Issue #2101)

259bc73

Removed unusual promote_scalar from beta_proportion (Issue #2101)

cd86fc5

Merge commit '0e419e94ad682521ed113c1947adc0452af76340' into HEAD

17b6b6d

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

1058731

…4.1 (tags/RELEASE_600/final)

Removed direction reverse checks (Issue #2101)

c77799b

Merge branch 'feature/varmat-dist-tests' of github.com:stan-dev/math …

d488d68

…into feature/varmat-dist-tests

Worked around bug in bernoulli and fixed expression thing in von mise…

d02ad05

…s lpdf (Issue #2101)

bbbales2 reviewed Jan 12, 2021

View reviewed changes

yashikno and others added 6 commits January 12, 2021 22:57

Merge commit '7085ef69bdb399db7d918240659f56305885a2fd' into HEAD

e7668fc

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

e64bdc3

…4.1 (tags/RELEASE_600/final)

Update gamma tests to work with new autodiff initializations (Issue #…

d3da2bc

…2101)

Made normal cdf test work with new autodiff initializations (Issue #2101

38874d1

)

Merge branch 'feature/varmat-dist-tests' of github.com:stan-dev/math …

2933d92

…into feature/varmat-dist-tests

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

05ed31c

…4.1 (tags/RELEASE_600/final)

bbbales2 changed the title ~~[WIP] Add tests for var_value<Matrix> for univariate distributions~~ Add tests for var_value<Matrix> for univariate distributions Jan 13, 2021

bbbales2 and others added 4 commits January 13, 2021 09:03

Removing extra difficult autodiff initialization (Issue #2101)

85b52bd

Fixed scalar_seq_view operator[] for varmat (Issue #2101)

d2eec67

Merge commit 'ce84d1903b479c016b51b9255e05d36f6f3e1741' into HEAD

daff60a

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

dd3f0f8

…4.1 (tags/RELEASE_600/final)

Merge remote-tracking branch 'origin/develop' into feature/varmat-dis…

034d009

…t-tests

SteveBronder commented Jan 26, 2021

View reviewed changes

test/prob/gamma/gamma_ccdf_log_test.hpp Outdated Show resolved Hide resolved

SteveBronder and others added 3 commits January 30, 2021 17:23

Merge remote-tracking branch 'origin/develop' into feature/varmat-dis…

9482b54

…t-tests

fix division for fvar to cast to double

0dd58c2

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

4114b9a

…4.1 (tags/RELEASE_600/final)

Reverting new test stuff, remove unnecessary value_ofs (Issue #2101)

7c2c8dd

stan-buildbot and others added 4 commits February 1, 2021 15:06

[Jenkins] auto-formatting by clang-format version 6.0.0-1ubuntu2~16.0…

86611b7

…4.1 (tags/RELEASE_600/final)

Merge remote-tracking branch 'origin/develop' into feature/varmat-dis…

ac312e2

…t-tests

Updated skew_double_exponential to support varmat (Issue #2101)

5dfbb26

Merge branch 'feature/varmat-dist-tests' of github.com:stan-dev/math …

46e49f8

…into feature/varmat-dist-tests

Merge remote-tracking branch 'origin/develop' into feature/varmat-dis…

57d4438

…t-tests

bbbales2 approved these changes Feb 4, 2021

View reviewed changes

bbbales2 merged commit 24eeaad into develop Feb 4, 2021

rok-cesnovar deleted the feature/varmat-dist-tests branch February 4, 2021 16:19

rok-cesnovar mentioned this pull request Feb 6, 2021

Revert "Add tests for var_value<Matrix> for univariate distributions" #2355

Merged

bbbales2 mentioned this pull request Mar 23, 2021

fvar<double> operator/ acting weird #2307

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add tests for var_value<Matrix> for univariate distributions #2304

Add tests for var_value<Matrix> for univariate distributions #2304

SteveBronder commented Jan 11, 2021

bbbales2 left a comment

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

SteveBronder Jan 26, 2021 •

edited

Loading

bbbales2 Jan 26, 2021 •

edited

Loading

SteveBronder Jan 31, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021

bbbales2 Jan 12, 2021 •

edited

Loading

stan-buildbot commented Jan 14, 2021

bbbales2 commented Jan 14, 2021

SteveBronder Jan 26, 2021

SteveBronder Jan 26, 2021

bbbales2 Jan 26, 2021

SteveBronder Jan 31, 2021

stan-buildbot commented Jan 27, 2021

SteveBronder commented Jan 31, 2021

bbbales2 commented Feb 1, 2021

SteveBronder commented Feb 1, 2021

stan-buildbot commented Feb 2, 2021

stan-buildbot commented Feb 4, 2021

Add tests for var_value<Matrix> for univariate distributions #2304

Add tests for var_value<Matrix> for univariate distributions #2304

Conversation

SteveBronder commented Jan 11, 2021

Summary

Tests

Side Effects

Release notes

Checklist

bbbales2 left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

SteveBronder Jan 26, 2021 • edited Loading

Choose a reason for hiding this comment

bbbales2 Jan 26, 2021 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

bbbales2 Jan 12, 2021 • edited Loading

Choose a reason for hiding this comment

stan-buildbot commented Jan 14, 2021

bbbales2 commented Jan 14, 2021

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

stan-buildbot commented Jan 27, 2021

SteveBronder commented Jan 31, 2021

bbbales2 commented Feb 1, 2021

SteveBronder commented Feb 1, 2021

stan-buildbot commented Feb 2, 2021

stan-buildbot commented Feb 4, 2021

SteveBronder Jan 26, 2021 •

edited

Loading

bbbales2 Jan 26, 2021 •

edited

Loading

bbbales2 Jan 12, 2021 •

edited

Loading