OnlineSPEC
[ICML 2026] [OnlineSPEC] When Drafts Evolve: Speculative Decoding Meets Online Learning
File Explorer
- framework.png
- OnlineSPEC_Logo_new.jpg
- config.json
- prepare_data.py
- __init__.py
- choices.py
- cnets.py
- configs.py
- ea_model.py
- kv_cache.py
- modeling_llama_kv.py
- modeling_mixtral_kv.py
- utils.py
- utils_alpha.py
- utils_c.py
- __init__.py
- choices.py
- cnets.py
- configs.py
- ea_model.py
- kv_cache.py
- modeling_llama_kv.py
- utils.py
- utils_c.py
- __init__.py
- modeling_eagle.py
- __init__.py
- choices.py
- cnets.py
- cnets1.py
- configs.py
- ea_model.py
- kv_cache.py
- modeling_llama_kv.py
- modeling_mixtral_kv.py
- modeling_qwen2_kv.py
- modeling_qwen3_kv.py
- utils.py
- utils_c.py
- eagle-ens.sh
- eagle-offline.sh
- eagle-online.sh
- eagle-train.sh
- eagle3-ens.sh
- eagle3-offline.sh
- eagle3-online.sh
- eagle3-train.sh
- hyper.sh
- osd-offline.sh
- osd-online.sh
- cnets.py
- config.json
- configs.py
- modeling_llama_kv.py
- train.py
- eval_eagle3.py
- evaluation.py
- load_data.py
- pipeline.py
- pipeline_eagle3.py
- pipeline_eagle3_ens.py
- pipeline_eagle3_hedge.py
- pipeline_ens.py
- pipeline_hedge.py
- pipeline_osd.py
- requirements.txt
- train.py
- traineagle3.py
- vanilla_speculative_decoding.py
- prepare_data.py
- __init__.py
- build_hidden_states.py
- partition_train_test.py
- __init__.py
- cli.py
- __init__.py
- cross_attention_head.py
- eagle_head.py
- mlp_head.py
- prefix_mlp_head.py
- __init__.py
- hydra_choices.py
- hydra_model.py
- kv_cache.py
- modeling_llama_kv.py
- utils.py
- __init__.py
- train.py
- utils.py
- __init__.py
- hf_utils.py
- run.sh
- train.sh
- eval.py
- load_data.py
- pipeline.py
- train.py
- prepare_data.py
- reproduce.sh
- __init__.py
- lr.py
- lr_tree.py
- vllm_model.py
- test_gsm8k.py
- test_math.py
- test_mbpp.py
- test_mmlu.py
- baseline.py
- dataset.py
- dpo_train.py
- main.py
- pipeline.py
- requirements.txt
- sft_dataset.py
- sft_train.py
- __init__.py
- chunking.py
- eagle_config.py
- prepare_data.py
- .gitignore
- README.md
# 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):
huggingface-cli
View Details ▼
huggingface-cli
This command is an alias of `hf`.
tldr hf
View documentation for the original command:
pip install
View Details ▼
pip install
Install Python packages.
pip install {{package1 package2 ...}}
Install one or more packages:
pip install {{package1 package2 ...}} {{[-U|--upgrade]}}
Upgrade all specified packages to the latest version, installing any that are not already present:
pip install {{package}}=={{version}}
Install a specific version of a package:
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:
