TensorRT-LLMs/tests/unittest/_torch
Ludwig Schneider 41ce14ab04
[None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314)
Signed-off-by: Ludwig Schneider <lschneider@nvidia.com>
2025-12-07 09:43:26 -08:00
..
attention [None] [feat] Optimize the algorithm part of RocketKV (#9333) 2025-12-01 09:04:09 +08:00
auto_deploy [#9602][feat] AutoDeploy: Support TRTLLM Sampler (#9641) 2025-12-04 19:24:11 -08:00
compilation [TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 2025-05-09 11:04:01 +08:00
debugger Fix: fix nvbug 5356427 (#5464) 2025-06-25 22:24:26 +08:00
executor [None][refactor] Improve request processing function in sampler (#9671) 2025-12-05 16:41:49 +01:00
misc [TRTLLM-9372][feat] Enable CuteDSL MoE with Large EP (#9592) 2025-12-05 22:08:52 -08:00
modeling [FMDL-1328][feat] Add support for nano-v3 and super-v3 with pytorch backend (#9261) 2025-12-02 13:40:20 +08:00
models/checkpoints/hf [TRTLLM-7136][feat] Update load_weights method to include mapping parameter in checkpoint loaders (#9583) 2025-12-05 16:07:20 +01:00
modules [TRTLLM-9372][feat] Enable CuteDSL MoE with Large EP (#9592) 2025-12-05 22:08:52 -08:00
multi_gpu [None][feat] Enable NCCL_SYMMETRIC as default fallback for AllReduce (#9314) 2025-12-07 09:43:26 -08:00
multi_gpu_modeling [https://nvbugs/5515753][ci] Add NCCL_DEBUG=INFO flag to collect more info with CI failure. (#8440) 2025-11-20 12:43:13 -05:00
multimodal [None][fix] InputProcessor config naming convention fix (#8705) 2025-11-03 22:29:21 -08:00
ray_orchestrator [TRTLLM-9144][fix] enhance RPC robustness (#8711) 2025-12-02 21:37:59 +08:00
sampler [None][refactor] Improve request processing function in sampler (#9671) 2025-12-05 16:41:49 +01:00
speculative [TRTLLM-6756][feat] Add Beam Search to TorchSampler (#8509) 2025-12-01 18:48:04 +01:00
thop [TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature (#9682) 2025-12-06 02:24:51 -08:00
helpers.py [#8733][feat] Add Llama4 MoE handling to AutoDeploy (#9556) 2025-12-04 08:03:33 +02:00
pattern_watcher.py [TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 2025-05-09 11:04:01 +08:00
test_connector.py [None][feat] KV Cache Connector API (#7228) 2025-08-28 23:09:27 -04:00