Shanshan ShenandGitHub fe57be7809 [MM][CG] Support --enable-vit-cuda-graph option for VLM examples (#40580) ...

Signed-off-by: shen-shanshan <467638484@qq.com>

2026-04-22 22:46:14 -07:00

..

disaggregated-prefill-v1

…

kv_load_failure_recovery

…

logits_processor

…

openai_batch

…

qwen2_5_omni

…

qwen3_omni

…

async_llm_streaming.py

…

audio_language.py

[model] support FireRedLID (#39290)

2026-04-10 08:43:58 +00:00

automatic_prefix_caching.py

…

batch_llm_inference.py

…

chat_with_tools.py

…

context_extension.py

…

data_parallel.py

…

disaggregated_prefill.py

…

encoder_decoder_multimodal.py

[model] support FireRedLID (#39290)

2026-04-10 08:43:58 +00:00

extract_hidden_states.py

Fix shape comment in extract_hidden_states example (#38723)

2026-04-01 07:29:33 -07:00

llm_engine_example.py

…

llm_engine_reset_kv.py

…

load_sharded_state.py

…

lora_with_quantization_inference.py

…

mistral-small.py

…

mlpspeculator.py

…

multilora_inference.py

…

pause_resume.py

…

prefix_caching_flexkv.py

…

prefix_caching.py

…

prompt_embed_inference.py

…

qwen_1m.py

…

reproducibility.py

…

routed_experts_e2e.py

…

run_one_batch.py

…

save_sharded_state.py

…

simple_profiling.py

…

skip_loading_weights_in_engine_init.py

…

spec_decode.py

…

structured_outputs.py

…

torchrun_dp_example.py

…

torchrun_example.py

…

vision_language_multi_image.py

Add Granite 4.1 Vision as built-in multimodal model (#40282)

2026-04-21 05:43:39 -07:00

vision_language.py

[MM][CG] Support --enable-vit-cuda-graph option for VLM examples (#40580)

2026-04-22 22:46:14 -07:00