Update Primus docs for 26.1 release (#5911)

* archive previous versions update conf fix fix docker hub url fix * update history pages * update docker info * update configs * update primus commit
2026-04-27 03:01:52 -04:00 · 2026-01-30 12:51:13 -05:00
parent 2da4c460ad
commit d8b6ee47e3
23 changed files with 3814 additions and 232 deletions
--- a/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml
@@ -1,15 +1,13 @@
 docker:
-  pull_tag: rocm/primus:v25.10
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
  components:
    ROCm: 7.1.0
-    Primus: 0.3.0
-    Primus Turbo: 0.1.1
    PyTorch: 2.10.0.dev20251112+rocm7.1
    Python: "3.10"
-    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Transformer Engine: 2.6.0.dev0+f141f34b
    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-09ab7153e2
+    hipBLASLt: 34459f66ea
    Triton: 3.4.0
    RCCL: 2.27.7
 model_groups:
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.11-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/megatron-lm-v25.11-benchmark-models.yaml
@@ -0,0 +1,47 @@
+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
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.11-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v25.11-benchmark-models.yaml
@@ -0,0 +1,58 @@
+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: primus_pyt_megatron_lm_train_llama-3.3-70b
+        config_name: llama3.3_70B-pretrain.yaml
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
+        config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
+      - model: Llama 2 7B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
+        config_name: llama2_7B-pretrain.yaml
+      - model: Llama 2 70B
+        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
+        config_name: llama2_70B-pretrain.yaml
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
+      - model: DeepSeek-V2-Lite
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
+        config_name: deepseek_v2_lite-pretrain.yaml
+  - group: Mistral AI
+    tag: mistral
+    models:
+      - model: Mixtral 8x7B
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
+        config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
+  - group: Qwen
+    tag: qwen
+    models:
+      - model: Qwen 2.5 7B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
+        config_name: primus_qwen2.5_7B-pretrain.yaml
+      - model: Qwen 2.5 72B
+        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
+        config_name: qwen2.5_72B-pretrain.yaml
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.11-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v25.11-benchmark-models.yaml
@@ -0,0 +1,32 @@
+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
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_train_llama-3.1-8b
+        model_repo: Llama-3.1-8B
+        url: https://huggingface.co/meta-llama/Llama-3.1-8B
+        precision: BF16
+      - model: Llama 3.1 70B
+        mad_tag: primus_pyt_train_llama-3.1-70b
+        model_repo: Llama-3.1-70B
+        url: https://huggingface.co/meta-llama/Llama-3.1-70B
+        precision: BF16
+  - group: DeepSeek
+    tag: deepseek
+    models:
+      - model: DeepSeek V3 16B
+        mad_tag: primus_pyt_train_deepseek-v3-16b
+        model_repo: DeepSeek-V3
+        url: https://huggingface.co/deepseek-ai/DeepSeek-V3
+        precision: BF16
--- a/docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.11-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/previous-versions/pytorch-training-v25.11-benchmark-models.yaml
@@ -0,0 +1,195 @@
+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
+model_groups:
+  - group: Meta Llama
+    tag: llama
+    models:
+    - model: Llama 4 Scout 17B-16E
+      mad_tag: pyt_train_llama-4-scout-17b-16e
+      model_repo: Llama-4-17B_16E
+      url: https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.3 70B
+      mad_tag: pyt_train_llama-3.3-70b
+      model_repo: Llama-3.3-70B
+      url: https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 3.2 1B
+      mad_tag: pyt_train_llama-3.2-1b
+      model_repo: Llama-3.2-1B
+      url: https://huggingface.co/meta-llama/Llama-3.2-1B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 3B
+      mad_tag: pyt_train_llama-3.2-3b
+      model_repo: Llama-3.2-3B
+      url: https://huggingface.co/meta-llama/Llama-3.2-3B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3.2 Vision 11B
+      mad_tag: pyt_train_llama-3.2-vision-11b
+      model_repo: Llama-3.2-Vision-11B
+      url: https://huggingface.co/meta-llama/Llama-3.2-11B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.2 Vision 90B
+      mad_tag: pyt_train_llama-3.2-vision-90b
+      model_repo: Llama-3.2-Vision-90B
+      url: https://huggingface.co/meta-llama/Llama-3.2-90B-Vision
+      precision: BF16
+      training_modes: [finetune_fw]
+    - model: Llama 3.1 8B
+      mad_tag: pyt_train_llama-3.1-8b
+      model_repo: Llama-3.1-8B
+      url: https://huggingface.co/meta-llama/Llama-3.1-8B
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora, HF_pretrain]
+    - model: Llama 3.1 70B
+      mad_tag: pyt_train_llama-3.1-70b
+      model_repo: Llama-3.1-70B
+      url: https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct
+      precision: BF16
+      training_modes: [pretrain, finetune_fw, finetune_lora]
+    - model: Llama 3.1 405B
+      mad_tag: pyt_train_llama-3.1-405b
+      model_repo: Llama-3.1-405B
+      url: https://huggingface.co/meta-llama/Llama-3.1-405B
+      precision: BF16
+      training_modes: [finetune_qlora]
+    - model: Llama 3 8B
+      mad_tag: pyt_train_llama-3-8b
+      model_repo: Llama-3-8B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 3 70B
+      mad_tag: pyt_train_llama-3-70b
+      model_repo: Llama-3-70B
+      url: https://huggingface.co/meta-llama/Meta-Llama-3-70B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 7B
+      mad_tag: pyt_train_llama-2-7b
+      model_repo: Llama-2-7B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora, finetune_qlora]
+    - model: Llama 2 13B
+      mad_tag: pyt_train_llama-2-13b
+      model_repo: Llama-2-13B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Llama 2 70B
+      mad_tag: pyt_train_llama-2-70b
+      model_repo: Llama-2-70B
+      url: https://github.com/meta-llama/llama-models/tree/main/models/llama2
+      precision: BF16
+      training_modes: [finetune_lora, finetune_qlora]
+  - group: OpenAI
+    tag: openai
+    models:
+    - model: GPT OSS 20B
+      mad_tag: pyt_train_gpt_oss_20b
+      model_repo: GPT-OSS-20B
+      url: https://huggingface.co/openai/gpt-oss-20b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+    - model: GPT OSS 120B
+      mad_tag: pyt_train_gpt_oss_120b
+      model_repo: GPT-OSS-120B
+      url: https://huggingface.co/openai/gpt-oss-120b
+      precision: BF16
+      training_modes: [HF_finetune_lora]
+  - group: DeepSeek
+    tag: deepseek
+    models:
+    - model: DeepSeek V2 16B
+      mad_tag: primus_pyt_train_deepseek-v2
+      model_repo: DeepSeek-V2
+      url: https://huggingface.co/deepseek-ai/DeepSeek-V2
+      precision: BF16
+      training_modes: [pretrain]
+  - group: Qwen
+    tag: qwen
+    models:
+    - model: Qwen 3 8B
+      mad_tag: pyt_train_qwen3-8b
+      model_repo: Qwen3-8B
+      url: https://huggingface.co/Qwen/Qwen3-8B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 3 32B
+      mad_tag: pyt_train_qwen3-32b
+      model_repo: Qwen3-32
+      url: https://huggingface.co/Qwen/Qwen3-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 32B
+      mad_tag: pyt_train_qwen2.5-32b
+      model_repo: Qwen2.5-32B
+      url: https://huggingface.co/Qwen/Qwen2.5-32B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2.5 72B
+      mad_tag: pyt_train_qwen2.5-72b
+      model_repo: Qwen2.5-72B
+      url: https://huggingface.co/Qwen/Qwen2.5-72B
+      precision: BF16
+      training_modes: [finetune_lora]
+    - model: Qwen 2 1.5B
+      mad_tag: pyt_train_qwen2-1.5b
+      model_repo: Qwen2-1.5B
+      url: https://huggingface.co/Qwen/Qwen2-1.5B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+    - model: Qwen 2 7B
+      mad_tag: pyt_train_qwen2-7b
+      model_repo: Qwen2-7B
+      url: https://huggingface.co/Qwen/Qwen2-7B
+      precision: BF16
+      training_modes: [finetune_fw, finetune_lora]
+  - group: Stable Diffusion
+    tag: sd
+    models:
+    - model: Stable Diffusion XL
+      mad_tag: pyt_huggingface_stable_diffusion_xl_2k_lora_finetuning
+      model_repo: SDXL
+      url: https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+      precision: BF16
+      training_modes: [posttrain]
+  - group: Flux
+    tag: flux
+    models:
+    - model: FLUX.1-dev
+      mad_tag: pyt_train_flux
+      model_repo: Flux
+      url: https://huggingface.co/black-forest-labs/FLUX.1-dev
+      precision: BF16
+      training_modes: [posttrain]
+  - group: NCF
+    tag: ncf
+    models:
+    - model: NCF
+      mad_tag: pyt_ncf_training
+      model_repo:
+      url: https://github.com/ROCm/FluxBenchmark
+      precision: FP32
+  - group: DLRM
+    tag: dlrm
+    models:
+    - model: DLRM v2
+      mad_tag: pyt_train_dlrm
+      model_repo: DLRM
+      url: https://github.com/AMD-AGI/DLRMBenchmark
+      training_modes: [pretrain]
--- a/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
@@ -1,13 +1,13 @@
 docker:
-  pull_tag: rocm/primus:v25.11
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
  components:
    ROCm: 7.1.0
    PyTorch: 2.10.0.dev20251112+rocm7.1
    Python: "3.10"
-    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Transformer Engine: 2.6.0.dev0+f141f34b
    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-09ab7153e2
+    hipBLASLt: 34459f66ea
    Triton: 3.4.0
    RCCL: 2.27.7
 model_groups:
--- a/docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml
@@ -1,13 +1,13 @@
 docker:
-  pull_tag: rocm/primus:v25.11
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
  components:
    ROCm: 7.1.0
    PyTorch: 2.10.0.dev20251112+rocm7.1
    Python: "3.10"
-    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Transformer Engine: 2.6.0.dev0+f141f34b
    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-09ab7153e2
+    hipBLASLt: 34459f66ea
 model_groups:
  - group: Meta Llama
    tag: llama
--- a/docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
+++ b/docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml
@@ -1,15 +1,13 @@
 docker:
-  pull_tag: rocm/primus:v25.10
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v25.10/images/sha256-140c37cd2eeeb183759b9622543fc03cc210dc97cbfa18eeefdcbda84420c197
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
  components:
    ROCm: 7.1.0
-    Primus: 0.3.0
-    Primus Turbo: 0.1.1
    PyTorch: 2.10.0.dev20251112+rocm7.1
    Python: "3.10"
-    Transformer Engine: 2.4.0.dev0+32e2d1d4
+    Transformer Engine: 2.6.0.dev0+f141f34b
    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-09ab7153e2
+    hipBLASLt: 34459f66ea
 model_groups:
  - group: Meta Llama
    tag: llama