vllm/transformers_utils/configs · tduncan/Nvidia-Optimization-Stack-VLLM · siGit Code & Deploy

@tduncan / Nvidia-Optimization-Stack-VLLM

Code Commits Issues Pulls Cloud Agent CI/CD

main

speculators

__init__.py

afmoe.py

AXK1.py

bagel.py

bailing_moe_v3_vl.py

chatglm.py

colmodernvbert.py

colpali.py

colqwen3.py

cosmos3.py

cosmos3_edge.py

deepseek_v4.py

deepseek_v41.py

deepseek_vl2.py

diffusion_gemma.py

dots3_note.py

dotsocr.py

eagle.py

extract_hidden_states.py

falcon.py

funaudiochat.py

gemma4.py

granite4_vision.py

hy_v3.py

hy_v4.py

hyperclovax.py

isaac.py

k3_dspark.py

kimi_k25.py

kimi_k3.py

kimi_linear.py

kimi_vl.py

lfm2_moe.py

medusa.py

midashenglm.py

mimo_v2_omni.py

minimax_m3.py

mistral.py

mlp_speculator.py

moondream3.py

moonvit.py

moss_transcribe_diarize.py

muse_glimmer.py

nemotron.py

nemotron_h.py

olmo_hybrid.py

openvla.py

ovis.py

parakeet.py

qianfan_ocr.py

qwen3_5.py

qwen3_5_moe.py

qwen3_asr.py

qwen3_next.py

radio.py

step3_vl.py

step3p5.py

ultravox.py

unlimited_ocr.py