diff --git a/docs/code-docs/source/conf.py b/docs/code-docs/source/conf.py
index cb00d0d6be45..fab292764f9f 100644
--- a/docs/code-docs/source/conf.py
+++ b/docs/code-docs/source/conf.py
@@ -20,7 +20,7 @@
 author = 'Microsoft'
 
 # The full version, including alpha/beta/rc tags
-release = '0.3.0'
+release = '0.6'
 
 master_doc = 'index'
 
diff --git a/docs/code-docs/source/memory.rst b/docs/code-docs/source/memory.rst
index 5c92dc199aa4..5b29312a0064 100644
--- a/docs/code-docs/source/memory.rst
+++ b/docs/code-docs/source/memory.rst
@@ -7,9 +7,9 @@ API To Estimate Memory Usage
 
 ZeRO2:
 
-.. autofunction:: deepspeed.runtime.zero.stage2.estimate_zero2_model_states_mem_needs_all_live
+.. autofunction:: deepspeed.runtime.zero.stage_1_and_2.estimate_zero2_model_states_mem_needs_all_live
 
-.. autofunction:: deepspeed.runtime.zero.stage2.estimate_zero2_model_states_mem_needs_all_cold
+.. autofunction:: deepspeed.runtime.zero.stage_1_and_2.estimate_zero2_model_states_mem_needs_all_cold
 
 Examples:
 
@@ -18,7 +18,7 @@ Let's try a 3B model with just 1 node with 8 gpus, using live model:
 .. code-block:: bash
 
     python -c 'from transformers import AutoModel; \
-    from deepspeed.runtime.zero.stage2 import estimate_zero2_model_states_mem_needs_all_live; \
+    from deepspeed.runtime.zero.stage_1_and_2 import estimate_zero2_model_states_mem_needs_all_live; \
     model = AutoModel.from_pretrained("t5-3b"); \
     estimate_zero2_model_states_mem_needs_all_live(model, num_gpus_per_node=8, num_nodes=1)'
     Estimated memory needed for params, optim states and gradients for a:
@@ -34,7 +34,7 @@ faster as we don't need to load the model.
 
 .. code-block:: bash
 
-    python -c 'from deepspeed.runtime.zero.stage2 import estimate_zero2_model_states_mem_needs_all_cold; \
+    python -c 'from deepspeed.runtime.zero.stage_1_and_2 import estimate_zero2_model_states_mem_needs_all_cold; \
     estimate_zero2_model_states_mem_needs_all_cold(total_params=2851e6, num_gpus_per_node=8, num_nodes=1)'
     Estimated memory needed for params, optim states and gradients for a:
     HW: Setup with 1 node, 8 GPUs per node.
diff --git a/requirements/requirements-readthedocs.txt b/requirements/requirements-readthedocs.txt
index f3ffe3b615a2..83f3b3e39b08 100644
--- a/requirements/requirements-readthedocs.txt
+++ b/requirements/requirements-readthedocs.txt
@@ -1,5 +1,8 @@
 docutils<0.18
 hjson
+packaging
 psutil
+py-cpuinfo
+pydantic
 torch
 tqdm