..
attention_backend
[None][feat] Add a standalone buffer cache class and reuse buffers between cduagraph and no-graph flow ( #7669 )
2025-09-26 07:28:06 -07:00
auto_deploy
[ #4674 ][bugfix] AutoDeploy Fix memory leak in fuse_moe ( #7844 )
2025-09-29 11:01:07 +03:00
compilation
[None][chore] Mass integration of release/1.0 - 3rd ( #7519 )
2025-09-08 14:03:04 +08:00
custom_ops
[ https://nvbugs/5518713 ][fix] Trtllm-gen moe backend for blockwise fp8 ckpt (Qwen3-235B-A22B-FP8) ( #7856 )
2025-09-26 14:29:32 -07:00
cute_dsl_kernels
[TRTLLM-6898][feat] Add swapab, tileN64, cga sync support for cute dsl nvfp4 gemm ( #7764 )
2025-09-18 21:20:04 +08:00
debug
Add debug hook to support dump tensor data and add new debug functions easily ( #5182 )
2025-06-24 17:45:28 +08:00
distributed
[TRTLLM-5966][feat] Helix: add alltoall op ( #6815 )
2025-09-25 07:18:29 -07:00
models
[None][chore] Disable concurrent weights loading for _load_weights_im… ( #8034 )
2025-09-28 07:11:16 -04:00
modules
[None][fix] only support deepep post quant all2all on nvfp4 ( #8041 )
2025-09-29 14:37:50 +08:00
peft
[TRTLLM-7346][fix] Improve performance of PyTorchModelEngine._get_lora_params_from_requests ( #7033 )
2025-08-25 10:37:40 +03:00
pyexecutor
[None][chore] Cherry-pick from ( #7598 ) Make low_precision_combine as a llm arg ( #7898 )
2025-09-28 22:32:33 -04:00
shared_tensor
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes ( #5396 )
2025-07-10 05:12:53 +09:00
speculative
[TRTLLM-8271][fix] Fix CDL overlap scheduling performance ( #7971 )
2025-09-26 16:05:10 -04:00
__init__.py
[nvbugs/5401156][fix] Avoid import all models when import trtllm._common ( #6266 )
2025-07-27 23:29:21 -04:00
autotuner.py
[TRTLLM-4500][feat] Add serialization/deserialization options for AutoTuner profiling cache ( #7738 )
2025-09-29 07:40:51 +08:00
cute_dsl_utils.py
[None][chore] polish error message in cute_dsl_utils.py ( #7852 )
2025-09-19 12:05:11 +08:00
expert_statistic.py
Add MTP support for Online EPLB ( #5213 )
2025-06-25 07:58:13 +08:00
flashinfer_utils.py
[None][ci] move unittests to sub-directories ( #6635 )
2025-08-20 05:42:22 -04:00
hostfunc.py
[TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) ( #6948 )
2025-09-03 15:16:11 -07:00
llm.py
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default ( #5312 )
2025-06-20 03:01:10 +08:00
memory_buffer_utils.py
[None][feat] Add a standalone buffer cache class and reuse buffers between cduagraph and no-graph flow ( #7669 )
2025-09-26 07:28:06 -07:00
metadata.py
[None][feat] Use Separate QKV Input Layout for Context MLA ( #6538 )
2025-08-19 22:04:48 +08:00
model_config.py
[None][chore] Cherry-pick from ( #7598 ) Make low_precision_combine as a llm arg ( #7898 )
2025-09-28 22:32:33 -04:00
utils.py
[TRTLLM-7330][feat] Eagle3 cuda graph support for the first draft model inference ( #7363 )
2025-09-26 11:28:05 +08:00
virtual_memory.py
[TRTLLM-4406][feat] LLM sleep & wakeup Part 1: virtual device memory ( #5034 )
2025-08-04 13:51:01 +08:00
b2095aa074