[model] feat: support ByteDance Seed-OSS 36B model (#3347)

### What does this PR do?

support ByteDance Seed-OSS 36B model:
1. add RL and SFT example
2. support mfu metrics

Requirement:
pip install transformers>=4.56.0

Notes: vllm v0.10.0 does not support Seed-OSS, but can fail back to
transformers to get it working.

### Checklist Before Starting

- [x] Search for similar PRs. Paste at least one query link here: ...
- [x] Format the PR title as `[{modules}] {type}: {description}` (This
will be checked by the CI)
- `{modules}` include `fsdp`, `megatron`, `sglang`, `vllm`, `rollout`,
`trainer`, `ci`, `training_utils`, `recipe`, `hardware`, `deployment`,
`ray`, `worker`, `single_controller`, `misc`, `perf`, `model`, `algo`,
`env`, `tool`, `ckpt`, `doc`, `data`
- If this PR involves multiple modules, separate them with `,` like
`[megatron, fsdp, doc]`
  - `{type}` is in `feat`, `fix`, `refactor`, `chore`, `test`
- If this PR breaks any API (CLI arguments, config, function signature,
etc.), add `[BREAKING]` to the beginning of the title.
  - Example: `[BREAKING][fsdp, megatron] feat: dynamic batching`

### Test

(TaskRunner pid=373084) step:2 - global_seqlen/min:6260 -
global_seqlen/max:11318 - global_seqlen/minmax_diff:5058 -
global_seqlen/balanced_min:8466 - global_seqlen/balanced_max:8468 -
global_seqlen/mean:8467.375 - actor/entropy:0.47251570224761963 -
actor/kl_loss:0.03297248564194888 - actor/kl_coef:0.001 -
actor/pg_loss:-0.0494408356025815 -
actor/pg_clipfrac:0.019900403218343854 -
actor/ppo_kl:0.020935473148711026 -
actor/pg_clipfrac_lower:9.349289757665247e-05 -
actor/grad_norm:0.47875913605093956 - perf/mfu/actor:0.2823303751694612
- perf/max_memory_allocated_gb:134.74115753173828 -
perf/max_memory_reserved_gb:141.615234375 -
perf/cpu_memory_used_gb:150.75712203979492 - actor/lr:1e-06 -
training/global_step:2 - training/epoch:0 - critic/score/mean:0.3515625
- critic/score/max:1.0 - critic/score/min:0.0 -
critic/rewards/mean:0.3515625 - critic/rewards/max:1.0 -
critic/rewards/min:0.0 - critic/advantages/mean:-0.023741308599710464 -
critic/advantages/max:0.7071057558059692 -
critic/advantages/min:-0.7071057558059692 -
critic/returns/mean:-0.023741308599710464 -
critic/returns/max:0.7071057558059692 -
critic/returns/min:-0.7071057558059692 -
response_length/mean:444.4296875 - response_length/max:1024.0 -
response_length/min:50.0 - response_length/clip_ratio:0.140625 -
response_length_non_aborted/mean:444.4296875 -
response_length_non_aborted/max:1024.0 -
response_length_non_aborted/min:50.0 -
response_length_non_aborted/clip_ratio:0.140625 -
response/aborted_ratio:0.0 - prompt_length/mean:84.78125 -
prompt_length/max:141.0 - prompt_length/min:54.0 -
prompt_length/clip_ratio:0.0 -
timing_s/start_profile:6.250300793908536e-05 -
timing_s/generate_sequences:21.979598999023438 -
timing_s/generation_timing/max:22.295286178588867 -
timing_s/generation_timing/min:21.753456115722656 -
timing_s/generation_timing/topk_ratio:0.125 -
timing_s/gen:39.58543623800506 - timing_s/reward:0.031087818002561107 -
timing_s/old_log_prob:17.46088112698635 - timing_s/ref:5.804751824995037
- timing_s/adv:0.003937039989978075 -
timing_s/update_actor:57.383965655986685 -
timing_s/step:120.27422251200187 -
timing_s/stop_profile:6.923600449226797e-05 -
timing_per_token_ms/gen:0.6958608511260053 -
timing_per_token_ms/ref:0.08569290696637147 -
timing_per_token_ms/adv:5.8120727940744256e-05 -
timing_per_token_ms/update_actor:0.8471333449857052 -
perf/total_num_tokens:67739 - perf/time_per_step:120.27422251200187 -
perf/throughput:70.40057980133741
### API and Usage Example

> Demonstrate how the API changes if any, and provide usage example(s)
if possible.

```python
# Add code snippet or script demonstrating how to use this
```

### Design & Code Changes

> Demonstrate the high-level design if this PR is complex, and list the
specific changes.

### Checklist Before Submitting

> [!IMPORTANT]
> Please check all the following items before requesting a review,
otherwise the reviewer might deprioritize this PR for review.

- [ x] Read the [Contribute
Guide](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md).
- [ x] Apply [pre-commit
checks](https://github.com/volcengine/verl/blob/main/CONTRIBUTING.md#code-linting-and-formatting):
`pre-commit install && pre-commit run --all-files --show-diff-on-failure
--color=always`
- [ x] Add / Update [the
documentation](https://github.com/volcengine/verl/tree/main/docs).
- [ x] Add unit or end-to-end test(s) to [the CI
workflow](https://github.com/volcengine/verl/tree/main/.github/workflows)
to cover all the code. If not feasible, explain why: ...
- [ x] Once your PR is ready for CI, send a message in [the `ci-request`
channel](https://verl-project.slack.com/archives/C091TCESWB1) in [the
`verl` Slack
workspace](https://join.slack.com/t/verl-project/shared_invite/zt-3855yhg8g-CTkqXu~hKojPCmo7k_yXTQ).
(If not accessible, please try [the Feishu group
(飞书群)](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=772jd4f1-cd91-441e-a820-498c6614126a).)

examples/grpo_trainer/run_seed_oss_36b.sh

@@ -0,0 +1,48 @@
+set -x
+
+python3 -m verl.trainer.main_ppo \
+    algorithm.adv_estimator=grpo \
+    data.train_files=$HOME/data/gsm8k/train.parquet \
+    data.val_files=$HOME/data/gsm8k/test.parquet \
+    data.train_batch_size=64 \
+    data.max_prompt_length=512 \
+    data.max_response_length=1024 \
+    data.filter_overlong_prompts=True \
+    data.truncation='error' \
+    actor_rollout_ref.model.path=ByteDance-Seed/Seed-OSS-36B-Base \
+    actor_rollout_ref.actor.optim.lr=1e-6 \
+    actor_rollout_ref.model.use_remove_padding=True \
+    actor_rollout_ref.model.enable_gradient_checkpointing=True \
+    actor_rollout_ref.model.use_fused_kernels=True \
+    actor_rollout_ref.actor.ppo_mini_batch_size=8 \
+    actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=2 \
+    actor_rollout_ref.actor.use_kl_loss=True \
+    actor_rollout_ref.actor.kl_loss_coef=0.001 \
+    actor_rollout_ref.actor.kl_loss_type=low_var_kl \
+    actor_rollout_ref.actor.entropy_coeff=0 \
+    actor_rollout_ref.actor.use_dynamic_bsz=True \
+    actor_rollout_ref.actor.strategy=fsdp2 \
+    actor_rollout_ref.rollout.log_prob_use_dynamic_bsz=True \
+    actor_rollout_ref.actor.fsdp_config.param_offload=True \
+    actor_rollout_ref.actor.fsdp_config.param_offload=True \
+    actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=2 \
+    actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
+    actor_rollout_ref.rollout.name=vllm \
+    actor_rollout_ref.rollout.gpu_memory_utilization=0.6 \
+    actor_rollout_ref.rollout.n=2 \
+    actor_rollout_ref.rollout.free_cache_engine=True \
+    actor_rollout_ref.ref.log_prob_use_dynamic_bsz=True \
+    actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=2 \
+    actor_rollout_ref.ref.fsdp_config.param_offload=True \
+    actor_rollout_ref.ref.strategy=fsdp2 \
+    algorithm.use_kl_in_reward=False \
+    trainer.critic_warmup=0 \
+    trainer.logger='["console"]' \
+    trainer.project_name='verl_grpo_seed_oss_36b' \
+    trainer.experiment_name='seed_oss_36b' \
+    trainer.val_before_train=False \
+    trainer.n_gpus_per_node=8 \
+    trainer.nnodes=1 \
+    trainer.save_freq=20 \
+    trainer.test_freq=5 \
+    trainer.total_epochs=15 $@

examples/sft/gsm8k/run_seed_oss_36b_sft.sh

@@ -0,0 +1,31 @@
+set -x
+
+if [ "$#" -lt 2 ]; then
+    echo "Usage: run_seed_oss_36b_sft.sh <nproc_per_node> <save_path> [other_configs...]"
+    exit 1
+fi
+
+nproc_per_node=$1
+save_path=$2
+
+# Shift the arguments so $@ refers to the rest
+shift 2
+
+torchrun --standalone --nnodes=1 --nproc_per_node=$nproc_per_node \
+     -m verl.trainer.fsdp_sft_trainer \
+    data.train_files=$HOME/data/gsm8k/train.parquet \
+    data.val_files=$HOME/data/gsm8k/test.parquet \
+    data.prompt_key=extra_info \
+    data.response_key=extra_info \
+    optim.lr=1e-4 \
+    data.prompt_dict_keys=['question'] \
+    +data.response_dict_keys=['answer'] \
+    data.micro_batch_size=4 \
+    model.partial_pretrain=ByteDance-Seed/Seed-OSS-36B-Base \
+    trainer.default_local_dir=$save_path \
+    trainer.project_name=gsm8k-sft \
+    trainer.experiment_name=gsm8k-sft-seed-oss-36b \
+    trainer.logger=console \
+    trainer.total_training_steps=1 \
+    ulysses_sequence_parallel_size=2 \
+    use_remove_padding=true $@

verl/utils/flops_counter.py

@@ -30,6 +30,7 @@ VALID_CONFIG_TYPE = {
     "minicpmo",
     "mistral",
     "gemma3_text",
+    "seed_oss",
 }
 
 
@@ -130,6 +131,7 @@ class FlopsCounter:
             "minicpmo": self._estimate_qwen2_flops,
             "mistral": self._estimate_qwen2_flops,
             "gemma3_text": self._estimate_gemma3_flops,
+            "seed_oss": self._estimate_qwen2_flops,
         }
         self.config = config