mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-11-02 19:03:06 +00:00
peterjunparkandGitHub
69bae1073f
* archive previous versions update conf fix fix docker hub url fix * update history pages * update docker info * update configs * update primus commit
48 lines
1.5 KiB
YAML
48 lines
1.5 KiB
YAML
docker:
|
|
pull_tag: rocm/primus:v25.11
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.11/images/sha256-71aa65a9bfc8e9dd18bce5b68c81caff864f223e9afa75dc1b719671a1f4a3c3
|
|
components:
|
|
ROCm: 7.1.0
|
|
PyTorch: 2.10.0.dev20251112+rocm7.1
|
|
Python: "3.10"
|
|
Transformer Engine: 2.4.0.dev0+32e2d1d4
|
|
Flash Attention: 2.8.3
|
|
hipBLASLt: 1.2.0-09ab7153e2
|
|
Triton: 3.4.0
|
|
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
|