github/ROCm
1
1
Fork 0
mirror of https://github.com/ROCm/ROCm.git synced 2026-04-05 03:01:17 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Megatron-LM training benchmark doc for v25.6 release (#5064)

Browse Source
This commit is contained in:
Peter Park
2025-07-18 15:57:25 -04:00
committed by GitHub
parent 7e7e15a201
commit 5bcf3b0847
10 changed files with 1296 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
View File

@@ -1,29 +1,60 @@
megatron-lm_benchmark:
model_groups:
- group: Meta Llama
tag: llama
models:
dockers:
- pull_tag: rocm/megatron-lm:v25.6_py312
docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py312/images/sha256-482ff906532285bceabdf2bda629bd32cb6174d2d07f4243a736378001b28df0
components:
ROCm: 6.4.1
PyTorch: 2.8.0a0+git7d205b2
Python: 3.12
Transformer Engine: 2.1.0.dev0+8c4a512
hipBLASLt: 393e413
Triton: 3.3.0
RCCL: 2.23.4.7a84c5d
doc_name: Ubuntu 24.04 + Python 3.12
- pull_tag: rocm/megatron-lm:v25.6_py310
docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.6_py310/images/sha256-9627bd9378684fe26cb1a10c7dd817868f553b33402e49b058355b0f095568d6
components:
ROCm: 6.4.1
PyTorch: 2.8.0a0+git7d205b2
Python: "3.10"
Transformer Engine: 2.1.0.dev0+8c4a512
hipBLASLt: 393e413
Triton: 3.3.0
RCCL: 2.23.4.7a84c5d
doc_name: Ubuntu 22.04 + Python 3.10
model_groups:
- group: Meta 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 3.1 70B (proxy)
mad_tag: pyt_megatron_lm_train_llama-3.1-70b-proxy
- 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
- group: DeepSeek
tag: deepseek
models:
- model: DeepSeek-V3 (proxy)
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 AI
tag: mistral
models:
- group: Mistral AI
tag: mistral
models:
- model: Mixtral 8x7B
mad_tag: pyt_megatron_lm_train_mixtral-8x7b
- model: Mixtral 8x22B
- model: Mixtral 8x22B (proxy)
mad_tag: pyt_megatron_lm_train_mixtral-8x22b-proxy
- group: Qwen
tag: qwen
models:
- model: Qwen 2.5 7B
mad_tag: pyt_megatron_lm_train_qwen2.5-7b
- model: Qwen 2.5 72B
mad_tag: pyt_megatron_lm_train_qwen2.5-72b

29
docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.5-benchmark-models.yaml Normal file
View File

@@ -0,0 +1,29 @@
megatron-lm_benchmark:
model_groups:
- group: Meta 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 AI
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