Add Megatron-LM benchmark doc 5/2 (#4778)

* reorg files

* add tabs

* update template

* update template

* update wordlist and toc

* add previous version to doc

* add selector paragraph

* update wordlist.txt

(cherry picked from commit 9ed65a81c4)

.wordlist.txt

@@ -272,6 +272,7 @@ NBIO
 NBIOs
 NCCL
 NCF
+NFS
 NIC
 NICs
 NLI
@@ -500,6 +501,7 @@ ZenDNN
 accuracies
 activations
 addr
+ade
 ai
 alloc
 allocatable
@@ -515,6 +517,7 @@ avx
 awk
 backend
 backends
+bb
 benchmarked
 benchmarking
 bfloat
@@ -538,6 +541,7 @@ cd
 centos
 centric
 changelog
+checkpointing
 chiplet
 cmake
 cmd
@@ -578,6 +582,7 @@ de
 deallocation
 debuggability
 debian
+deepseek
 denoise
 denoised
 denoises
@@ -601,6 +606,7 @@ embeddings
 enablement
 encodings
 endfor
+endif
 endpgm
 enqueue
 env
@@ -702,6 +708,7 @@ migratable
 miopen
 miopengemm
 mivisionx
+mixtral
 mjx
 mkdir
 mlirmiopen
@@ -843,6 +850,7 @@ subfolder
 subfolders
 submodule
 submodules
+subnet
 supercomputing
 symlink
 symlinks

docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml

@@ -0,0 +1,29 @@
+megatron-lm_benchmark:
+  model_groups:
+    - group: Llama
+      tag: llama
+      models:
+      - model: Llama 3.3 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.3-70b
+      - model: Llama 3.1 8B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-8b
+      - model: Llama 3.1 70B
+        mad_tag: pyt_megatron_lm_train_llama-3.1-70b
+      - model: Llama 2 7B
+        mad_tag: pyt_megatron_lm_train_llama-2-7b
+      - model: Llama 2 70B
+        mad_tag: pyt_megatron_lm_train_llama-2-70b
+    - group: DeepSeek
+      tag: deepseek
+      models:
+      - model: DeepSeek-V3
+        mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
+      - model: DeepSeek-V2-Lite
+        mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
+    - group: Mistral
+      tag: mistral
+      models:
+      - model: Mixtral 8x7B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x7b
+      - model: Mixtral 8x22B
+        mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy

docs/sphinx/_toc.yml.in

@@ -44,11 +44,11 @@ subtrees:
         title: Training
         subtrees:
         - entries:
-          - file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm
+          - file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
             title: Train a model with Megatron-LM
-          - file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training
+          - file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
             title: Train a model with PyTorch
-          - file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext
+          - file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
             title: Train a model with JAX MaxText
           - file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
             title: Train a model with LLM Foundry
@@ -78,9 +78,9 @@ subtrees:
             title: Run models from Hugging Face
           - file: how-to/rocm-for-ai/inference/llm-inference-frameworks.rst
             title: LLM inference frameworks
-          - file: how-to/rocm-for-ai/inference/vllm-benchmark.rst
+          - file: how-to/rocm-for-ai/inference/benchmark-docker/vllm.rst
             title: vLLM inference performance testing
-          - file: how-to/rocm-for-ai/inference/pytorch-inference-benchmark.rst
+          - file: how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
             title: PyTorch inference performance testing
           - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
             title: Deploy your model