mirror of
https://github.com/hanzoai/ROCm.git
synced 2026-11-02 19:03:06 +00:00
peterjunparkandGitHub
4d156fcbb3
* add previous versions * Fix heading levels in pages using embedded templates (#5468) * update primus-megatron doc update megatron-lm doc update templates fix tab update primus-megatron model configs Update primus-pytorch model configs fix css class add posttrain to pytorch-training template update data sheets update update update update docker tags * Add known issue and update Primus/Turbo versions * add primus ver to histories * update primus ver to 0.1.1 * fix leftovers from merge conflict
49 lines
1.6 KiB
YAML
49 lines
1.6 KiB
YAML
dockers:
|
|
- pull_tag: rocm/megatron-lm:v25.8_py310
|
|
docker_hub_url: https://hub.docker.com/layers/rocm/megatron-lm/v25.8_py310/images/sha256-50fc824361054e445e86d5d88d5f58817f61f8ec83ad4a7e43ea38bbc4a142c0
|
|
components:
|
|
ROCm: 6.4.3
|
|
PyTorch: 2.8.0a0+gitd06a406
|
|
Python: "3.10"
|
|
Transformer Engine: 2.2.0.dev0+54dd2bdc
|
|
hipBLASLt: d1b517fc7a
|
|
Triton: 3.3.0
|
|
RCCL: 2.22.3
|
|
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 (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
|