Yukun He a1645c922b Fallback to NCCL for various patterns when input size is large. (#4009) ... When input size is larger than the max workspace size, we shall fallback to NCCL + corresponding pre/post function to ensure the functionality of AllReduce. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com>		2025-05-01 15:17:16 -07:00
..
attention_backend	fix: change the seq_lens sync copy to an async one (#3786)	2025-04-29 23:56:49 +08:00
auto_deploy	[AutoDeploy] Make all ranks agree on kv-cache size (#4007)	2025-05-02 04:07:28 +08:00
compilation	Unify two versions of AllReduce custom op (#3032)	2025-04-22 21:58:42 +08:00
custom_ops	Clean up allreduce op in Deepseek V3 model. (#3829)	2025-05-01 07:56:36 +08:00
distributed	Fallback to NCCL for various patterns when input size is large. (#4009)	2025-05-01 15:17:16 -07:00
models	feat: LogitsProcessor in PyTorch backend (#3145)	2025-05-01 14:15:30 -07:00
modules	feat: LogitsProcessor in PyTorch backend (#3145)	2025-05-01 14:15:30 -07:00
peft	add passing E2E LoRA flow (#3788)	2025-04-23 18:38:06 +03:00
pyexecutor	feat: LogitsProcessor in PyTorch backend (#3145)	2025-05-01 14:15:30 -07:00
speculative	feat: add relaxed acceptance for DS (#3865)	2025-05-01 21:50:36 +08:00
__init__.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00
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
llm.py	test: [TRTLLM-4334] Create 1.0 criteria scope from API stability references (#3069)	2025-03-26 18:14:35 +08:00
metadata.py	feat: no-cache attention in PyTorch workflow (#3085)	2025-04-05 01:54:32 +08:00
model_config.py	Fix fp8 kvcache (#3877)	2025-04-29 10:31:10 +08:00
pipeline_interface.py	chore: bump version to 0.19.0 (#3598) (#3841)	2025-04-29 16:57:22 +08:00
utils.py	refactor: (part1) Add contraints doc for fusedMoe module. (#3882)	2025-04-29 22:23:02 +08:00