mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-11-02 19:03:06 +00:00
54 lines
1.9 KiB
YAML
54 lines
1.9 KiB
YAML
dockers:
|
|
MI355X and MI350X:
|
|
pull_tag: rocm/megatron-lm:v25.9_gfx950
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx950/images/sha256-1a198be32f49efd66d0ff82066b44bd99b3e6b04c8e0e9b36b2c481e13bff7b6
|
|
components: &docker_components
|
|
ROCm: 7.0.0
|
|
Primus: aab4234
|
|
PyTorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
|
|
Python: "3.10"
|
|
Transformer Engine: 2.2.0.dev0+54dd2bdc
|
|
Flash Attention: 2.8.3
|
|
hipBLASLt: 911283acd1
|
|
Triton: 3.4.0+rocm7.0.0.git56765e8c
|
|
RCCL: 2.26.6
|
|
MI325X and MI300X:
|
|
pull_tag: rocm/megatron-lm:v25.9_gfx942
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.9_gfx942/images/sha256-df6ab8f45b4b9ceb100fb24e19b2019a364e351ee3b324dbe54466a1d67f8357
|
|
components: *docker_components
|
|
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 (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:
|
|
- model: Mixtral 8x7B
|
|
mad_tag: pyt_megatron_lm_train_mixtral-8x7b
|
|
- 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
|