Code & Deploy
siGit Code
Git Hosting
Toggle menu
siGit Code
Git Hosting
Sign in
Sign in
@tduncan
/
Nvidia-Optimization-Stack-VLLM
Nvidia-Optimization-Stack-VLLM
/
vllm
/
model_executor
/
models
Code
Commits
Issues
Pulls
Cloud Agent
CI/CD
main
main
transformers
__init__.py
adapters.py
afmoe.py
aimv2.py
apertus.py
aria.py
audioflamingo3.py
AXK1.py
bagel.py
bailing_moe.py
bailing_moe_linear.py
bailing_moe_mtp.py
bailing_moe_v3.py
bailing_moe_v3_mtp.py
bailing_moe_v3_vl.py
bee.py
bert.py
bert_with_rope.py
blip.py
blip2.py
bloom.py
chatglm.py
clip.py
cohere2_moe.py
cohere2_vision.py
cohere_asr.py
cohere_compass.py
cohere_eagle.py
colbert.py
colmodernvbert.py
colpali.py
colqwen3.py
colqwen3_5.py
commandr.py
config.py
conformer_encoder.py
cosmos3.py
cosmos3_edge.py
dbrx.py
deepencoder.py
deepencoder2.py
deepseek_eagle.py
deepseek_eagle3.py
deepseek_mtp.py
deepseek_ocr.py
deepseek_ocr2.py
deepseek_v2.py
deepseek_vl2.py
diffusion_gemma.py
diffusion_gemma_sampler.py
dots_ocr.py
eagle2_5_vl.py
ernie45.py
ernie45_moe.py
ernie45_vl.py
ernie45_vl_moe.py
ernie_mtp.py
exaone.py
exaone4.py
exaone4_5.py
exaone4_5_mtp.py
exaone_moe.py
exaone_moe_mtp.py
extract_hidden_states.py
falcon.py
falcon_h1.py
fireredasr2.py
funasr.py
funaudiochat.py
gemma.py
gemma2.py
gemma3.py
gemma3_mm.py
gemma3n.py
gemma3n_audio_utils.py
gemma3n_mm.py
gemma4.py
gemma4_dspark.py
gemma4_mm.py
gemma4_mtp.py
gemma4_unified.py
glm4.py
glm4_1v.py
glm4_moe.py
glm4_moe_lite.py
glm4_moe_lite_mtp.py
glm4_moe_mtp.py
glm4v.py
glm_ocr.py
glm_ocr_mtp.py
glmasr.py
glmasr_utils.py
gpt2.py
gpt_j.py
gpt_oss.py
granite.py
granite4_vision.py
granite_speech.py
granite_speech_plus.py
granitemoe.py
granitemoehybrid.py
granitemoeshared.py
h2ovl.py
hrm_text.py
hy_v3.py
hy_v3_mtp.py
hyperclovax.py
hyperclovax_vision_v2.py
idefics2_vision_model.py
idefics3.py
interfaces.py
interfaces_base.py
intern_vit.py
internlm2.py
interns1.py
interns1_pro.py
interns1_vit.py
interns2_mobius.py
interns2_preview.py
internvl.py
iquest_loopcoder.py
isaac.py
jamba.py
jina.py
jina_vl.py
k2_horizon.py
kanana_v.py
keye.py
keye_vl1_5.py
kimi_audio.py
kimi_k25.py
kimi_k25_vit.py
kimi_vl.py
laguna.py
laguna_dflash.py
lfm2.py
lfm2_moe.py
lfm2_siglip2.py
lfm2_vl.py
lightonocr.py
lilicorr.py
llama.py
llama4.py
llama4_eagle.py
llama_eagle.py
llama_eagle3.py
llava.py
llava_next.py
llava_next_video.py
llava_onevision.py
llava_onevision2.py
longcat_flash.py
longcat_flash_mtp.py
longcat_flash_ngram.py
mamba.py
mamba2.py
medusa.py
midashenglm.py
mimo.py
mimo_audio.py
mimo_mtp.py
mimo_v2.py
mimo_v2_mtp.py
mimo_v2_omni.py
minicpm.py
minicpm3.py
minicpm_eagle.py
minicpmo.py
minicpmv.py
minicpmv4_6.py
minimax_m2.py
mistral.py
mistral3.py
mistral_eagle.py
mistral_large_3.py
mistral_large_3_eagle.py
mixtral.py
mllama4.py
mlp_speculator.py
modernbert.py
module_mapping.py
molmo.py
molmo2.py
moondream3.py
moonvit.py
moss_audio.py
moss_transcribe_diarize.py
muse_glimmer.py
nano_nemotron_vl.py
nemotron.py
nemotron_h.py
nemotron_h_mtp.py
nemotron_nas.py
nemotron_parse.py
nemotron_vl.py
nvlm_d.py
olmo_hybrid.py
olmoe.py
openai_privacy_filter.py
opencua.py
openpangu.py
openpangu_mtp.py
openpangu_vl.py
openvla.py
opt.py
orion.py
ovis.py
ovis2_5.py
paddleocr_vl.py
paligemma.py
parakeet.py
param2moe.py
phi3.py
phi3v.py
phi4mm.py
phi4mm_audio.py
phi4mm_utils.py
phi4siglip.py
phimoe.py
pixtral.py
plamo3.py
qianfan_ocr.py
qwen2.py
qwen2_5_omni_thinker.py
qwen2_5_vl.py
qwen2_audio.py
qwen2_moe.py
qwen2_rm.py
qwen2_vl.py
qwen3.py
qwen3_5.py
qwen3_5_mtp.py
qwen3_asr.py
qwen3_asr_forced_aligner.py
qwen3_asr_realtime.py
qwen3_dflash.py
qwen3_dflash2.py
qwen3_dspark.py
qwen3_eagle3.py
qwen3_moe.py
qwen3_next.py
qwen3_next_mtp.py
qwen3_omni_moe_thinker.py
qwen3_vl.py
qwen3_vl_moe.py
radio.py
registry.py
rnj1.py
roberta.py
rvl.py
sarvam.py
siglip.py
siglip2navit.py
skyworkr1v.py
smolvlm.py
solar.py
stablelm.py
step1.py
step3_text.py
step3_vl.py
step3p5.py
step3p5_mtp.py
step3p7.py
step_vl.py
telechat2.py
teleflm.py
terratorch.py
ultravox.py
unlimited_ocr.py
utils.py
vision.py
voxtral.py
voxtral_realtime.py
voyage.py
whisper.py
whisper_causal.py
whisper_utils.py
zamba2.py