mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-09-30 20:37:25 +00:00
peterjunparkandGitHub
1a7914662e
* archive previous version * update configs * update megatron page * update legacy configs * update * fix links
48 lines
1.5 KiB
YAML
48 lines
1.5 KiB
YAML
docker:
|
|
pull_tag: rocm/primus:v26.2
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
|
|
components:
|
|
ROCm: 7.2.0
|
|
PyTorch: 2.10.0+git94c6e04
|
|
Python: "3.12.3"
|
|
Transformer Engine: 2.8.0.dev0+51f74fa7
|
|
Flash Attention: 2.8.3
|
|
hipBLASLt: 34459f66ea
|
|
Triton: 3.5.0
|
|
RCCL: 2.27.7
|
|
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
|