Yukun He 9cc5922a0b Clean up allreduce op in Deepseek V3 model. (#3829) ... * Replace deepseek_allreduce op with the new unified allreduce op and moe_allreduce op. * Minor revision of moe_allreduce op argument names. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-05-01 07:56:36 +08:00
..
auto_deploy	feat: [AutoDeploy] generalizing cudagraph to multiple dynamic inputs (#3589)	2025-04-23 03:38:51 +08:00
compilation	Update (#2978)	2025-03-23 16:39:35 +08:00
modeling	feat: llama4 input processor (#3383)	2025-04-25 16:47:14 -07:00
modules	chore: reorganize some unit tests of PyTorch (#3780)	2025-04-23 11:19:10 -07:00
multi_gpu	Clean up allreduce op in Deepseek V3 model. (#3829)	2025-05-01 07:56:36 +08:00
multi_gpu_modeling	feat: llama4 input processor (#3383)	2025-04-25 16:47:14 -07:00
speculative	[fix] Fix flashinfer + speculation issues (#3686)	2025-04-28 14:34:22 -04:00
thop	TRTLLM-4624 feat: Add nvfp4 gemm and moe support for SM120 (#3770)	2025-04-29 11:19:11 -04:00
helpers.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
pattern_watcher.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
test_attention_mla.py	fix: Fix FMHA-based MLA in the generation phase and add MLA unit test (#3863)	2025-04-29 09:09:43 +08:00
test_attention_no_cache.py	refactor(test): remove random context sequence lengths and set seed for reproducibility in attention tests (#3919)	2025-04-29 10:08:04 +08:00
test_attention.py	reduce num layers in attention test (#3509)	2025-04-14 12:43:59 +08:00
test_autotuner.py	feat: Apply the new torch-flow compatible AutoTuner to both Fused MoE and NVFP4 Linear operators. (#3151)	2025-04-08 14:28:36 +08:00
test_flashinfer_attention.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00
test_flashinfer_star_attn.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00
test_mnnvl_memory.py	feat: Add MNNVL MoE A2A support (#3504)	2025-04-25 17:29:08 +08:00
test_overlap_scheduler_input.json	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
test_overlap_scheduler.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
test_pytorch_model_engine.py	chore: move all distributed related codes into _torch.distributed directory (#3511)	2025-04-15 08:39:17 +08:00
test_resource_manager.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
test_return_logits.py	feat: return logits in PyTorch flow (#3221)	2025-04-24 16:56:03 -07:00
test_trtllm_decoder.py	fix: Fix C++ decoder synchronization in PyTorch (#3106)	2025-04-23 23:55:27 +08:00
test_vanilla_attention.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00