torch>=2.9.1
packaging==26.0
huggingface_hub>=1.1.7
peft<0.20.0,>=0.19.1
tokenizers>=0.22.1
transformers==5.9.0
accelerate==1.13.0
datasets<4.9.0,>=4.8.4
trl==1.5.1
hf_xet==1.4.3
kernels==0.13.0
trackio>=0.16.1
typing-extensions>=4.15.0
optimum==1.16.2
hf_transfer
sentencepiece
gradio<7.0,>=6.2.0
modal==1.3.0.post1
pydantic>=2.10.6
addict
fire
PyYAML>=6.0
requests
wandb
einops
colorama
numba>=0.61.2
numpy>=2.2.6
typer<0.26.0
evaluate==0.4.1
scipy
nvidia-ml-py==12.560.30
art
tensorboard
python-dotenv==1.0.1
s3fs>=2024.5.0
gcsfs>=2025.3.0
adlfs>=2024.5.0
ocifs==1.3.2
zstandard==0.22.0
fastcore
lm_eval==0.4.11
langdetect==1.0.9
immutabledict==4.2.0
antlr4-python3-runtime==4.13.2
schedulefree==1.4.1
openenv-core==0.1.0
axolotl-contribs-lgpl==0.0.7
axolotl-contribs-mit==0.0.6
posthog==6.7.11
mistral-common==1.11.0

[:platform_machine != "aarch64"]
fla-core==0.4.1
flash-linear-attention==0.4.1

[:sys_platform != "darwin"]
bitsandbytes==0.49.1
triton>=3.4.0
liger-kernel==0.7.0

[:sys_platform != "darwin" and platform_machine != "aarch64"]
xformers>=0.0.33.post2
torchao==0.17.0

[apollo]
apollo-torch

[auto-gptq]
auto-gptq==0.5.1

[deepspeed]
deepspeed<0.19.0,>=0.18.6
deepspeed-kernels

[fbgemm-gpu]
fbgemm-gpu-genai>=1.3.0

[flash-attn]
flash-attn==2.8.3

[galore]
galore_torch

[llmcompressor]
llmcompressor>=0.10.0

[mamba-ssm]
mamba-ssm==1.2.0.post1
causal_conv1d

[mlflow]
mlflow

[opentelemetry]
opentelemetry-api
opentelemetry-sdk
opentelemetry-exporter-prometheus
prometheus-client

[optimizers]
galore_torch
apollo-torch
lomo-optim==0.1.1
torch-optimi==0.2.1
came_pytorch==0.1.3
q-galore-torch==1.0

[ray]
ray[train]>=2.52.1

[ring-flash-attn]
flash-attn==2.8.3
ring-flash-attn>=0.1.7

[vllm]
vllm>=0.15.0
