InfMem
No description available.
File Explorer
- Apptainerfile.rocm
- Dockerfile.ngc.vllm
- Dockerfile.ngc.vllm0.8
- Dockerfile.ngc.vllm0.8.sagemaker
- Dockerfile.rocm
- Dockerfile.sglang
- Dockerfile.stage1.megatron
- Dockerfile.stage2.megatron
- Dockerfile.vemlp.vllm.te
- aime.py
- full_hh_rlhf.py
- geo3k.py
- gsm8k.py
- gsm8k_multiturn_w_tools.py
- hellaswag.py
- math_dataset.py
- multiturn.py
- run_deepseek7b_mutli_node.sh
- run_deepseek_v2_lite_math.sh
- run_deepseek7b_llm.sh
- run_deepseek7b_llm_math.sh
- run_deepseek7b_llm_math_megatron.sh
- run_deepseek7b_llm_seq_balance.sh
- run_qwen2-7b.sh
- run_qwen2-7b_math.sh
- run_qwen2-7b_math_megatron.sh
- run_qwen2-7b_seq_balance.sh
- run_qwen2_5_vl-7b.sh
- naive_chat_scheduler.py
- run_deepseek7b_llm.sh
- run_deepseek7b_llm_modelscope.sh
- run_deepseek7b_llm_sp2.sh
- run_deepseek_full_hh_rlhf.sh
- run_deepseek_math_gsm8k_megatron.sh
- run_gemma.sh
- run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh
- run_qwen2-7b_math_gsm8k_megatron.sh
- run_qwen2-7b_rm.sh
- run_qwen2-7b_rm_seq_balance.sh
- run_qwen2-7b_seq_balance.sh
- run_qwen2-7b_sglang_seq_balance.sh
- run_qwen2.5-32b.sh
- verl_getting_started.ipynb
- tutorial.ipynb
- run_qwen2-7b_math_rf.sh
- run_qwen2-7b_math_rf_baseline.sh
- run_qwen2.5-3b_seq_balance.sh
- run_qwen2.5-7b_seq_balance.sh
- run_qwen2-7b.sh
- run_deepseek_6b7.sh
- run_gemma_2b.sh
- run_gemma_7b.sh
- run_qwen_05_peft.sh
- run_qwen_05_sp2.sh
- run_qwen_05_sp2_liger.sh
- run_qwen_05_sp2.sh
- ray_on_slurm.slurm
- ppo_trainer_split.yaml
- main_ppo_split.py
- README.md
- run_deepseek7b_llm.sh
- split_monkey_patch.py
- qwen2_14b_grpo_4_h800_fsdp_vllm.sh
- qwen2_32B_grpo_8_h20_megatron_vllm.sh
- qwen2-70b_grpo_32_h20_fsdp_vllm.sh
- qwen2-70b_grpo_32_h800_fsdp_vllm.sh
- qwen2-7b_grpo_2_h800_fsdp_vllm.sh
- benchmark_visualization.png
- INFMEM_FW.png
- performance_scatter_large_font.png
- tests.yml
- dependabot.yml
- plan-of-attack.png
- ddp.yaml
- fsdp.yaml
- zero2.yaml
- zero3.yaml
- config_demo.yaml
- filter_dapo.yaml
- filter_python.yaml
- config_demo.yaml
- config_v00.00.yaml
- config_v00.00.yaml
- config_distill.yaml
- config_demo.yaml
- config_demo_code.yaml
- config_demo_code_ioi.yaml
- config_codeforces.yaml
- prethink_memagent.yaml
- README.md
- compute_pass_rate.py
- launch_filtering.sh
- README.md
- benchmark_e2b.py
- decontaminate.py
- e2b_router.py
- generate_reasoning.py
- get_tensor_parallel_size.py
- morph_router.py
- run_benchmarks.py
- upload_details.py
- serve_r1_vllm.slurm
- launch_piston_workers.sh
- launch_single_piston.sh
- README.md
- compute_pass_rate.slurm
- e2b_router.slurm
- evaluate.slurm
- generate.slurm
- morph_router.slurm
- README.md
- serve_r1.slurm
- serve_router.slurm
- train.slurm
- __init__.py
- cf_scoring.py
- code_patcher.py
- ioi_scoring.py
- ioi_utils.py
- morph_client.py
- piston_client.py
- utils.py
- __init__.py
- callbacks.py
- code_providers.py
- data.py
- evaluation.py
- hub.py
- import_utils.py
- model_utils.py
- routed_morph.py
- routed_sandbox.py
- wandb_logging.py
- __init__.py
- configs.py
- generate.py
- grpo.py
- pretrain.py
- rewards.py
- sft.py
- sft_lora.py
- test_code_reward.py
- test_data.py
- __init__.py
- test_rewards.py
- .gitignore
- cached_fineweb_10B.py
- LICENSE
- Makefile
- README.md
- run_sft.sh
- setup.cfg
- setup.py
- paper.pdf
- dapo_trainer.yaml
- dapo_ray_trainer.py
- main_dapo.py
- prepare_dapo_data.sh
- README.md
- run_dapo_early_qwen2.5_32b.sh
- run_dapo_qwen2.5_32b.sh
- test_dapo_7b.sh
- README.md
- prime_trainer.yaml
- __init__.py
- main_prime.py
- prime_core_algos.py
- prime_dp_rm.py
- prime_fsdp_workers.py
- prime_ray_trainer.py
- run_prime_qwen.sh
- evaluation.yaml
- __init__.py
- gpqa.py
- livecodebench.py
- math.py
- __init__.py
- data_process.py
- main_eval.py
- README.md
- reward_score.py
- run_r1_distill_qwen.sh
- Qwen2TokenizerFast.j2
- Qwen2TokenizerFast_org.j2
- test.py
- utils.py
- async_memory.py
- infmem.py
- memory.py
- memory_prethink.py
- perf_distributed_tokenizer.py
- perf_encode.py
- perf_tokenizer.py
- test_async_generation_output.ipynb
- test_pad_tensor_list_to_length.py
- test_token_template.ipynb
- test_tool_tokenize.ipynb
- async_generation_manager.py
- async_utils.py
- generation_manager.py
- interface.py
- tool.py
- utils.py
- converter_hf_to_mcore.py
- diagnose.py
- merger.sh
- model_merger.py
- client.py
- hdfs.py
- llm070.py
- runtime_env.yaml
- __init__.py
- aio.py
- envs.py
- filter_rewrite_musique.py
- infmem.py
- metrics.py
- distill.py
- ruler_decomposed_distillation.py
- ruler_general_sft_distill.py
- ruler_hqa_sft_distill.py
- sft_filter.py
- vllm_serve.sh
- common_words_extraction.py
- constants.py
- freq_words_extraction.py
- nemo.py
- niah.py
- PaulGrahamEssays_URLs.txt
- qa.py
- synthetic.yaml
- tokenizer.py
- variable_tracking.py
- .gitignore
- convert_to_eval.py
- dataset_process.py
- different_docs_eval.py
- download_paulgraham_essay.py
- download_qa_dataset.sh
- filter.py
- filter2.py
- hotpotqa_verifier.py
- processing.py
- ruler_data_prepare.py
- ruler_data_prepare.sh
- template.py
- token_count.ipynb
- tools.py
- utils.py
- __init__.py
- aio.py
- boxed.py
- envs.py
- functions.py
- infmem.py
- metrics.py
- openai_api.py
- openai_retrieval.py
- qwenlong_cprs.py
- recurrent.py
- resp.py
- .gitignore
- longbench_task.py
- ruler_general.py
- ruler_hqa.py
- run.py
- test_laucher.sh
- visualize.py
- vllm_serve.sh
- .gitignore
- test_fsdp_ckpt.py
- run_all.sh
- test_tensor_dict.py
- create_dataset.py
- config.json
- create_model_tokenizer.py
- generation_config.json
- model.safetensors
- tokenizer_config.json
- main_trainer.py
- README.md
- __init__.py
- task.py
- tokenizer.py
- __init__.py
- run_function_reward.sh
- run_model_reward.sh
- run_sft.sh
- test_sp_loss_match.py
- __init__.py
- check_custom_rwd_fn.py
- check_results.py
- run_dapo.sh
- run_ppo_trainer_megatron.sh
- run_prime.sh
- run_r1_distill_qwen_aime24_eval.sh
- run_ray_trainer.sh
- run_ray_trainer_fire_sampling.sh
- run_ray_trainer_rmpad.sh
- run_test.sh
- run_gen_qwen05.sh
- test_memory_buffers.py
- test_ops.py
- test_torch_functional.py
- test_transformer.py
- test_transformers_ulysses.py
- main.py
- client.py
- README.md
- run.sh
- server.py
- test_check_worker_alive.py
- test_colocated_workers.py
- test_data_transfer.py
- test_driverfunc_to_worker.py
- test_high_level_scheduling_api.py
- test_ray_local_envs.py
- test_rvdz.py
- test_worker_group_basics.py
- test_worker_group_torch.py
- run_fsdp_vllm.py
- test_hf_rollout.py
- test_sglang_spmd.py
- test_vllm_hf_loader.py
- test_vllm_multi_turn.py
- test_vllm_spmd.py
- test_sandbox.py
- check_license.py
- test_import.py
- test_tensor_dict_utilities.py
- test_multiturn_sft_dataset.py
- test_rl_dataset.py
- test_rm_dataset.py
- test_sft_dataset.py
- test_import_utils.py
- test_module.py
- __init__.py
- kill_github_tests.sh
- __init__.py
- llama_loader.py
- llama_loader_depracated.py
- llama_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_llama_megatron.py
- __init__.py
- __init__.py
- config_converter.py
- loader.py
- model_forward.py
- model_initializer.py
- readme.md
- registry.py
- saver.py
- util.py
- weight_converter.py
- __init__.py
- qwen2_loader.py
- qwen2_loader_depracated.py
- qwen2_saver.py
- __init__.py
- parallel_attention.py
- parallel_decoder.py
- parallel_linear.py
- parallel_mlp.py
- parallel_rmsnorm.py
- __init__.py
- modeling_qwen2_megatron.py
- __init__.py
- __init__.py
- llama.py
- monkey_patch.py
- qwen2.py
- qwen2_vl.py
- __init__.py
- README.md
- registry.py
- weight_loader_registry.py
- __init__.py
- worker.py
- worker_group.py
- __init__.py
- ray.py
- __init__.py
- decorator.py
- worker.py
- worker_group.py
- __init__.py
- base.py
- megatron.py
- __init__.py
- __init__.py
- parallel_state.py
- __init__.py
- arg_utils.py
- config.py
- dtensor_weight_loaders.py
- hf_weight_loader.py
- llm.py
- llm_engine_sp.py
- megatron_weight_loaders.py
- model_loader.py
- model_runner.py
- parallel_state.py
- spmd_gpu_executor.py
- tokenizer.py
- worker.py
- __init__.py
- arg_utils.py
- config.py
- dtensor_weight_loaders.py
- hf_weight_loader.py
- llm.py
- llm_engine_sp.py
- megatron_weight_loaders.py
- model_loader.py
- model_runner.py
- parallel_state.py
- spmd_gpu_executor.py
- tokenizer.py
- worker.py
- __init__.py
- __init__.py
- evaluation.yaml
- generation.yaml
- ppo_megatron_trainer.yaml
- ppo_trainer.yaml
- sft_trainer.yaml
- __init__.py
- core_algos.py
- metric_utils.py
- ray_trainer.py
- reward.py
- __init__.py
- fsdp_sft_trainer.py
- main_eval.py
- main_generation.py
- main_ppo.py
- runtime_env.yaml
- __init__.py
- checkpoint_manager.py
- fsdp_checkpoint_manager.py
- megatron_checkpoint_manager.py
- __init__.py
- multiturn_sft_dataset.py
- README.md
- rl_dataset.py
- rm_dataset.py
- sft_dataset.py
- vision_utils.py
- __init__.py
- performance.py
- profile.py
- trajectory_tracker.py
- __init__.py
- aggregate_logger.py
- __init__.py
- memory.py
- optimizer.py
- pipeline_parallel.py
- sequence_parallel.py
- tensor_parallel.py
- __init__.py
- ray_backend.py
- __init__.py
- testing_util.py
- utils.py
- __init__.py
- grader.py
- math_normalize.py
- __init__.py
- geo3k.py
- gsm8k.py
- hotpotqa.py
- math.py
- math_batch.py
- math_dapo.py
- math_verify.py
- ruler.py
- __init__.py
- config.py
- distributed.py
- flops_counter.py
- fs.py
- fsdp_utils.py
- hdfs_io.py
- import_utils.py
- logging_utils.py
- megatron_utils.py
- memory_buffer.py
- model.py
- net_utils.py
- py_functional.py
- ray_utils.py
- seqlen_balancing.py
- tokenizer.py
- torch_dtypes.py
- torch_functional.py
- tracking.py
- ulysses.py
- vllm_utils.py
- version
- __init__.py
- base.py
- dp_actor.py
- megatron_actor.py
- __init__.py
- base.py
- dp_critic.py
- megatron_critic.py
- __init__.py
- batch.py
- dapo.py
- naive.py
- prime.py
- test_concur.py
- thread.py
- __init__.py
- reward_model.py
- __init__.py
- base.py
- __init__.py
- naive_rollout.py
- __init__.py
- sglang_rollout.py
- __init__.py
- fire_vllm_rollout.py
- vllm_async_server.py
- vllm_rollout.py
- vllm_rollout_spmd.py
- __init__.py
- async_server.py
- base.py
- hf_rollout.py
- tokenizer.py
- __init__.py
- base.py
- fsdp_sglang.py
- fsdp_ulysses.py
- fsdp_vllm.py
- megatron_vllm.py
- __init__.py
- fsdp_workers.py
- megatron_workers.py
- __init__.py
- protocol.py
- .gitignore
- .readthedocs.yaml
- hfd.sh
- infmem_4B.sh
- LICENSE
- memagent_4B.sh
- method.png
- Notice.txt
- quickstart.py
- README.md
- requirements.txt
- requirements_sglang.txt
- setup_vllm083.sh
- unfied_agent.png
# Use via CDN
jsDelivrjsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.
Command Glossary
Commands referenced in this DOCs, explained below.
conda activate
View Details ▼
conda activate
Activate a conda environment.
See also: `conda deactivate`.
conda activate myenv
Activate an existing environment named `myenv`:
conda activate {{path/to/myenv}}
Activate an existing environment located at custom path:
conda activate --stack myenv
Stack `myenv` environment on top of a previous environment making libraries/commands/variables from both accessible:
conda create
View Details ▼
conda create
Create new conda environments.
conda create {{[-y|--yes]}} {{[-n|--name]}} py39 python=3.9 "numpy>=1.11" scipy
Create a new environment named `py39`, install Python 3.9, NumPy v1.11 or above in it, and the latest stable version of SciPy. Say yes to all confirmations:
conda create {{[-n|--name]}} myenv --file {{file1.yml}} --file {{file2.yml}}
Create a new environment named `myenv` and install packages listed in files:
conda create {{[-p|--prefix]}} {{path/to/myenv}}
Create a new environment at a custom path (i.e. prefix):
git clone
View Details ▼
git clone
Clone an existing repository.
git clone {{remote_repository_location}} {{path/to/directory}}
Clone an existing repository into a new directory (the default directory is the repository name):
git clone --recursive {{remote_repository_location}}
Clone an existing repository and its submodules:
git clone {{[-n|--no-checkout]}} {{remote_repository_location}}
Clone only the `.git` directory of an existing repository:
python
View Details ▼
python
Python language interpreter.
python
Start a REPL (interactive shell):
python {{path/to/file.py}}
Execute a specific Python file:
python -i {{path/to/file.py}}
Execute a specific Python file and start a REPL:
