TensorRT-LLM/examples at main · NVIDIA/TensorRT-LLM

Name		Name	Last commit message	Last commit date
parent directory ..
apps		apps
arctic		arctic
baichuan		baichuan
bert		bert
bindings/executor		bindings/executor
blip2		blip2
bloom		bloom
chatglm		chatglm
cogvlm		cogvlm
commandr		commandr
cpp/executor		cpp/executor
cpp_library		cpp_library
dbrx		dbrx
deepseek_v1		deepseek_v1
deepseek_v2		deepseek_v2
dit		dit
draft_target_model		draft_target_model
eagle		eagle
enc_dec		enc_dec
exaone		exaone
falcon		falcon
gemma		gemma
gpt		gpt
gptj		gptj
gptneox		gptneox
grok		grok
infinitebench		infinitebench
internlm		internlm
internlm2		internlm2
jais		jais
llama		llama
llm-api		llm-api
lookahead		lookahead
mamba		mamba
medusa		medusa
mixtral		mixtral
mllama		mllama
model_api		model_api
mpt		mpt
multimodal		multimodal
nemotron		nemotron
nemotron_nas		nemotron_nas
openai_triton		openai_triton
opt		opt
phi		phi
prompt_lookup		prompt_lookup
python_plugin		python_plugin
quantization		quantization
qwen		qwen
qwenvl		qwenvl
recurrentgemma		recurrentgemma
redrafter		redrafter
sample_weight_stripping		sample_weight_stripping
sdxl		sdxl
skywork		skywork
smaug		smaug
whisper		whisper
eval_long_context.py		eval_long_context.py
generate_checkpoint_config.py		generate_checkpoint_config.py
hf_lora_convert.py		hf_lora_convert.py
mmlu.py		mmlu.py
run.py		run.py
summarize.py		summarize.py
utils.py		utils.py

Provide feedback