diff --git a/requirements.txt b/requirements.txt
index 5a6870cd3d8..b23bdc7cdb7 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -15,7 +15,7 @@ pathlib==1.0.1; python_version < "3.4"
 jsonschema>=2.6.0,<3.1.0
 # Development dependencies
 cython>=0.25
-pytest>=4.0.0,<4.1.0
+pytest>=4.6.5
 pytest-timeout>=1.3.0,<2.0.0
 mock>=2.0.0,<3.0.0
 flake8>=3.5.0,<3.6.0
diff --git a/spacy/syntax/_parser_model.pxd b/spacy/syntax/_parser_model.pxd
index 5aec986d2a2..9c72f34156b 100644
--- a/spacy/syntax/_parser_model.pxd
+++ b/spacy/syntax/_parser_model.pxd
@@ -36,7 +36,9 @@ cdef WeightsC get_c_weights(model) except *
 
 cdef SizesC get_c_sizes(model, int batch_size) except *
 
-cdef void resize_activations(ActivationsC* A, SizesC n) nogil
+cdef ActivationsC alloc_activations(SizesC n) nogil
+
+cdef void free_activations(const ActivationsC* A) nogil
 
 cdef void predict_states(ActivationsC* A, StateC** states,
         const WeightsC* W, SizesC n) nogil
diff --git a/spacy/syntax/_parser_model.pyx b/spacy/syntax/_parser_model.pyx
index 841e3343234..ce3dcbfa5a3 100644
--- a/spacy/syntax/_parser_model.pyx
+++ b/spacy/syntax/_parser_model.pyx
@@ -62,6 +62,21 @@ cdef SizesC get_c_sizes(model, int batch_size) except *:
     return output
 
 
+cdef ActivationsC alloc_activations(SizesC n) nogil:
+    cdef ActivationsC A
+    memset(&A, 0, sizeof(A))
+    resize_activations(&A, n)
+    return A
+
+
+cdef void free_activations(const ActivationsC* A) nogil:
+    free(A.token_ids)
+    free(A.scores)
+    free(A.unmaxed)
+    free(A.hiddens)
+    free(A.is_valid)
+
+
 cdef void resize_activations(ActivationsC* A, SizesC n) nogil:
     if n.states <= A._max_size:
         A._curr_size = n.states
diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx
index fa1a41fa4c4..9b45fb0f73e 100644
--- a/spacy/syntax/nn_parser.pyx
+++ b/spacy/syntax/nn_parser.pyx
@@ -27,7 +27,8 @@ from thinc.neural.util import get_array_module
 from thinc.linalg cimport Vec, VecVec
 import srsly
 
-from ._parser_model cimport resize_activations, predict_states, arg_max_if_valid
+from ._parser_model cimport alloc_activations, free_activations
+from ._parser_model cimport predict_states, arg_max_if_valid
 from ._parser_model cimport WeightsC, ActivationsC, SizesC, cpu_log_loss
 from ._parser_model cimport get_c_weights, get_c_sizes
 from ._parser_model import ParserModel
@@ -306,8 +307,7 @@ cdef class Parser:
             WeightsC weights, SizesC sizes) nogil:
         cdef int i, j
         cdef vector[StateC*] unfinished
-        cdef ActivationsC activations
-        memset(&activations, 0, sizeof(activations))
+        cdef ActivationsC activations = alloc_activations(sizes)
         while sizes.states >= 1:
             predict_states(&activations,
                 states, &weights, sizes)
@@ -321,6 +321,7 @@ cdef class Parser:
                 states[i] = unfinished[i]
             sizes.states = unfinished.size()
             unfinished.clear()
+        free_activations(&activations)
 
     def set_annotations(self, docs, states_or_beams, tensors=None):
         cdef StateClass state