TensorRT-LLMs

mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00

History

Kefeng-Duan 67949f7c39 Update README and add benchmarking blog for DeepSeek-R1 (#3232 ) - Added a new entry in the README for the published benchmarking best practices for DeepSeek-R1. - Introduced a new blog post detailing performance benchmarking configurations and procedures for DeepSeek-R1 in TensorRT-LLM, including installation, dataset preparation, and benchmarking steps for both B200 and H200 GPUs. Signed-off-by: taoli <litaotju@users.noreply.github.com> Co-authored-by: taoli <litaotju@users.noreply.github.com>		2025-04-10 17:00:49 +08:00
..
apps	doc: refactor trtllm-serve examples and doc (#3187 )	2025-04-04 11:40:43 +08:00
auto_deploy	feat: [TRTLLM-3510] DeepseekV3 support in AutoDeploy (#3281 )	2025-04-08 21:47:57 +08:00
bert	Update TensorRT-LLM (#2582 )	2024-12-16 21:50:47 -08:00
bindings/executor	Update TensorRT-LLM (#2582 )	2024-12-16 21:50:47 -08:00
commandr	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
cpp/executor	Update TensorRT-LLM (#2873 )	2025-03-11 21:13:42 +08:00
cpp_library	Update TensorRT-LLM (#1274 )	2024-03-12 18:15:52 +08:00
deepseek_v3	Update README and add benchmarking blog for DeepSeek-R1 (#3232 )	2025-04-10 17:00:49 +08:00
disaggregated	update readme for disaggregated (#3323 )	2025-04-07 21:29:15 +08:00
dora	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
draft_target_model	Doc: update steps of using Draft-Target-Model (DTM) in the documents. (#3366 )	2025-04-09 17:35:01 +08:00
eagle	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
enc_dec	doc: use alert formatting (#3153 )	2025-03-31 07:30:52 +08:00
exaone	Add EXAONE-Deep (#3054 )	2025-03-26 14:24:04 +08:00
gemma	feat: Add Gemma3 text-only model support (#3247 )	2025-04-10 12:34:58 +08:00
glm-4-9b	chore: clean some ci of qa test (#3083 )	2025-03-31 14:30:41 +08:00
gpt	fix: GPT-Next convert failure (#3220 )	2025-04-02 17:14:39 +08:00
granite	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
infinitebench	Update TensorRT-LLM (#1725 )	2024-06-04 20:26:32 +08:00
internlm2	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
language_adapter	Update TensorRT-LLM (#2873 )	2025-03-11 21:13:42 +08:00
llama	fix: fix for cp > kvHeadNum (#3002 )	2025-03-26 12:39:02 +08:00
llm-api	feat: use cudaMalloc to allocate kvCache (#3303 )	2025-04-08 10:59:14 +08:00
llm-eval/lm-eval-harness	Update (#2978 )	2025-03-23 16:39:35 +08:00
lookahead	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
mamba	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
medusa	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
mixtral	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
mllama	Add Llama 4 (#3302 )	2025-04-09 03:35:21 +08:00
models/contrib	chore: clean some ci of qa test (#3083 )	2025-03-31 14:30:41 +08:00
multimodal	test: add random image test for llama-3.2-11b-vision (#3055 )	2025-03-26 15:38:16 +08:00
nemotron	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
nemotron_nas	Update TensorRT-LLM (#2562 )	2024-12-11 00:31:05 -08:00
openai_triton	Update TensorRT-LLM (#2792 )	2025-02-18 21:27:39 +08:00
phi	Add support for Phi-4-mini (#2990 )	2025-04-02 08:34:39 +08:00
prompt_lookup	Doc: update steps of using Draft-Target-Model (DTM) in the documents. (#3366 )	2025-04-09 17:35:01 +08:00
python_plugin	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
pytorch	feat: Add Qwen2.5-VL and refactor Qwen2-VL (#3156 )	2025-04-10 04:09:03 +08:00
quantization	Add thread leak check and fix thread/memory leak issues. (#3270 )	2025-04-08 19:03:18 +08:00
qwen	fix: fix for cp > kvHeadNum (#3002 )	2025-03-26 12:39:02 +08:00
qwen2audio	chore: Handle qwen2audio inputs ids expansion during processing (#3080 )	2025-03-26 15:00:27 +08:00
qwenvl	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
recurrentgemma	Fix .gitmodules (#2852 )	2025-03-04 22:34:09 +08:00
redrafter	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
sample_weight_stripping	Update (#2978 )	2025-03-23 16:39:35 +08:00
scaffolding	feat: Enhance the integrated robustness of scaffolding with __init__.py #3305 (#3312 )	2025-04-09 21:13:47 +08:00
serve	doc: refactor trtllm-serve examples and doc (#3187 )	2025-04-04 11:40:43 +08:00
vit	Update (#2978 )	2025-03-23 16:39:35 +08:00
whisper	Update TensorRT-LLM (#2849 )	2025-03-04 18:44:00 +08:00
constraints.txt	chore: bump version to 0.19.0.dev2025041500 (#3360 )	2025-04-08 20:45:27 +08:00
eval_long_context.py	Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338 )	2025-04-08 23:51:27 +08:00
generate_checkpoint_config.py	Update TensorRT-LLM (#2562 )	2024-12-11 00:31:05 -08:00
generate_xgrammar_tokenizer_info.py	Update TensorRT-LLM (#2783 )	2025-02-13 18:40:22 +08:00
gpqa_llmapi.py	test: Add gpqa tests for DeepSeek models (#3063 )	2025-03-27 19:47:06 +08:00
hf_lora_convert.py	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
mmlu_llmapi.py	test: Accuracy test improvement (Part 2): Incorporate mmlu to accuracy test suite (#2982 )	2025-03-25 07:34:10 +08:00
mmlu.py	test: Accuracy test improvement (Part 2): Incorporate mmlu to accuracy test suite (#2982 )	2025-03-25 07:34:10 +08:00
run.py	Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338 )	2025-04-08 23:51:27 +08:00
summarize.py	Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338 )	2025-04-08 23:51:27 +08:00
utils.py	Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338 )	2025-04-08 23:51:27 +08:00