Yukun He 9e7182b603 [TRTLLM-9615][feat] Implement a distributed tuning system (#9621) ... Four distinct strategies are implemented to accommodate different distributed tuning scenarios, including BROADCAST, INDEPENDENT, MERGE, PARALLEL. * Distributed tuning is disabled by default, with the INDEPENDENT strategy as the fallback. This conservative approach prevents unexpected behavior in standard use cases. * Only operations with significant tuning time overhead have been assigned the PARALLEL strategy, which allows the same tensor parallelism (TP) rank to tune tactics concurrently across different ranks. This targeted approach balances performance gains with stability. * Operations with nested tuning structures, such as NVFP4GemmUnifiedRunner, currently support only the INDEPENDENT strategy. This restriction exists because the synchronization mechanism is optimized only for leaf operations and doesn't yet handle nested hierarchies. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-12-15 21:08:53 +08:00
..
apps	[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)	2025-09-25 21:02:35 +08:00
auto_deploy	[None][feat] AutoDeploy: prepare_metadata revisited (#9764)	2025-12-12 20:14:14 +08:00
bindings/executor	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
configs	[TRTC-43] [feat] Add config db and docs (#9420)	2025-12-12 04:00:03 +08:00
cpp/executor	[TRTLLM-9197][infra] Move thirdparty stuff to it's own listfile (#8986)	2025-11-20 16:44:23 -08:00
cpp_library	[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)	2025-09-25 21:02:35 +08:00
disaggregated	[None] [fix] Fix slrum scripts (#10007)	2025-12-15 04:20:53 -08:00
dora	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
draft_target_model	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
eagle	[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)	2025-09-25 21:02:35 +08:00
infinitebench	Update TensorRT-LLM (#1725)	2024-06-04 20:26:32 +08:00
language_adapter	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
layer_wise_benchmarks	[TRTLLM-9615][feat] Implement a distributed tuning system (#9621)	2025-12-15 21:08:53 +08:00
llm-api	[TRTLLM-9601][feat] Expose mmKeys for multimodal to integrate with dynamo. (#9604)	2025-12-15 08:42:30 +08:00
llm-eval/lm-eval-harness	[TRTLLM-9065][chore] remove PyTorchConfig completely (#8856)	2025-11-06 22:37:03 -08:00
longbench	[None] [feat] Optimize the algorithm part of RocketKV (#9333)	2025-12-01 09:04:09 +08:00
lookahead	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
medusa	[OMNIML-3036][doc] Re-branding TensorRT-Model-Optimizer as Nvidia Model-Optimizer (#9679)	2025-12-07 07:14:05 -08:00
models	[None][feat] Support Mistral Large3 LLM part (#9820)	2025-12-13 11:44:27 +08:00
ngram	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
openai_triton	[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)	2025-09-25 21:02:35 +08:00
opentelemetry	[None][chore] Change trt-server to trtlllm-server in opentelemetry readme (#9173)	2025-11-17 22:02:24 -08:00
python_plugin	[None][doc] Rename TensorRT-LLM to TensorRT LLM for homepage and the … (#7850)	2025-09-25 21:02:35 +08:00
quantization	[OMNIML-3036][doc] Re-branding TensorRT-Model-Optimizer as Nvidia Model-Optimizer (#9679)	2025-12-07 07:14:05 -08:00
ray_orchestrator	[None][chore] Use cached model in all ray tests (#8962)	2025-11-06 15:14:15 +01:00
redrafter	[None][chore] update torch_dtype -> dtype in 'transformers' (#8263)	2025-10-15 17:09:30 +09:00
sample_weight_stripping	[None][chore] Weekly mass integration of release/1.1 -- rebase (#9522)	2025-11-29 21:48:48 +08:00
scaffolding	[None][feat] Deep Research Implemented with Scaffolding (#8452)	2025-11-06 10:33:28 +08:00
serve	[TRTLLM-9860][doc] Add docs and examples for Responses API (#9946)	2025-12-14 21:46:13 -08:00
sparse_attention	[None][feat] Add RocketKV usage doc and e2e accuracy test on LongBenchV2 (#9572)	2025-12-03 11:33:46 +08:00
trtllm-eval	test: Add LLGuidance test and refine guided decoding (#5348)	2025-06-25 14:12:56 +08:00
wide_ep	[TRTLLM-9762] [doc] Update documents for GB300 NVL72 (#9987)	2025-12-14 19:30:28 -08:00
constraints.txt	[None][chore] bump version to 1.2.0rc6 (#9874)	2025-12-10 04:53:26 -08:00
eval_long_context.py	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
generate_checkpoint_config.py	[None][chroe] Rename TensorRT-LLM to TensorRT LLM for source code. (#7851)	2025-09-25 21:02:35 +08:00
generate_xgrammar_tokenizer_info.py	Update TensorRT-LLM (#2783)	2025-02-13 18:40:22 +08:00
hf_lora_convert.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
mmlu.py	[https://nvbugs/4141427][chore] Add more details to LICENSE file (#9881)	2025-12-13 08:35:31 +08:00
run.py	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
summarize.py	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00
utils.py	[None][feat] Support ignored prompt length for penalties via new sampling config parameter (#8127)	2025-10-27 13:12:31 -04:00