William Zhang a117e7a57e [TRTLLM-7442][model] Remove unnecessary D2H copies (#7273) ... * Why? Initial profiling showed there were multiple D2H / H2D copies being scheduled in the mistral 3.1 small model. * What? This commit removes those unnecessary copies by returning `image_sizes` as a simple list instead of a tensor. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2025-09-03 23:14:20 -04:00
..
attention_backend	[https://nvbugs/5374016][fix] improve error message (#6893)	2025-09-01 11:02:31 +08:00
auto_deploy	[#7222][autodeploy] Separate run_shape_prop as another graph utility (#7313)	2025-09-03 19:32:50 -04:00
compilation	[https://nvbugs/5485102][fix] Correctly set stride for piecewise outp… (#7442)	2025-09-04 10:48:15 +08:00
custom_ops	[None][chore] Wrap the swiglu into custom op to avoid redundant device copy. (#7021)	2025-08-27 13:02:10 +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	[https://nvbugs/5445466][fix] Bypass MLP TP split for MNNVL in DeepSeek V3 to avoid hanging. (#6886)	2025-08-28 15:17:48 -07:00
models	[TRTLLM-7442][model] Remove unnecessary D2H copies (#7273)	2025-09-03 23:14:20 -04:00
modules	[None][doc] fix example in docstring (#7410)	2025-09-02 11:59:49 +03:00
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] Remove two unused parameters in create_py_executor (#7458)	2025-09-04 07:31:31 +08:00
shared_tensor	[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes (#5396)	2025-07-10 05:12:53 +09:00
speculative	[TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) (#6948)	2025-09-03 15:16:11 -07:00
__init__.py	[nvbugs/5401156][fix] Avoid import all models when import trtllm._common (#6266)	2025-07-27 23:29:21 -04:00
autotuner.py	[None][perf] Make finalize fusion part of the tactic selection logic (#6915)	2025-08-21 14:08:03 -07:00
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
metadata.py	[None][feat] Use Separate QKV Input Layout for Context MLA (#6538)	2025-08-19 22:04:48 +08:00
model_config.py	[https://nvbugs/5445466][fix] Eliminate race when loading HF dynamic modules (#7268)	2025-08-29 12:36:30 +08:00
utils.py	[https://nvbugs/5485102][fix] Correctly set stride for piecewise outp… (#7442)	2025-09-04 10:48:15 +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