William Zhang c0ae6bbdbe [None][feat] EPD for Qwen3 VL (#10470) ... * Why? We would like to support EPD disaggregated serving for Qwen3 VL. * What? This commit adds such support, and extends existing unit tests for correctness checks. Some minor (protected) interface changes had to be made to the weight mapper as a side-effect. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2026-01-08 06:45:54 -05:00
..
_torch	[None][feat] EPD for Qwen3 VL (#10470)	2026-01-08 06:45:54 -05:00
api_stability	[TRTLLM-9654][feat] Support DeepSeek-V32 chat template (#9814)	2025-12-19 17:05:38 +08:00
bindings	[TRTLLM-9527][feat] Add transferAgent binding (step 1) (#10113)	2026-01-06 08:40:38 +08:00
disaggregated	[TRTLLM-8920][feat] decouple disagg service from fastapi (#8714)	2025-12-05 10:44:16 +08:00
executor	[https://nvbugs/5720482][fix] Fix test rpc streaming (#9902)	2025-12-13 01:14:43 -08:00
llmapi	[TRTLLM-9551][infra] Partition test_llm_pytorch.py for parallel execution (#10400)	2026-01-05 13:58:03 -05:00
others	[TRTLLM-9465][fix] Swap TP-CP grouping order (#10350)	2026-01-05 20:08:03 +08:00
scaffolding	[None][feat] Refactor scaffolding streaming feature and fix openai wo… (#8622)	2025-10-30 16:02:40 +08:00
tools	[None][feat] Layer-wise benchmarks: support TEP balance, polish slurm scripts (#10237)	2026-01-05 11:23:04 +08:00
trt	[TRTLLM-8682][chore] Remove auto_parallel module (#8329)	2025-10-22 20:53:08 -04:00
utils	[TRTLLM-8376][feat] top-p optimization (removes redundant softmax) (#9411)	2025-11-25 18:46:48 +01:00
conftest.py	[TRTLLM-9737][chore] Add rl perf reproduce script and enhance the robustness of Ray tests (#9939)	2025-12-24 15:27:01 +08:00
dump_checkpoint_stats.py
gc_utils.py	[nvbug 5273941] fix: broken cyclic reference detect (#5417)	2025-07-01 20:12:55 +08:00
profile_utils.py
pytest.ini	[TRTLLM-9181][feat] improve disagg-server prometheus metrics; synchronize workers' clocks when workers are dynamic (#9726)	2025-12-16 05:16:32 -08:00
test_model_runner_cpp.py
test_pip_install.py	[https://nvbugs/5616189][fix] Make more cases use local cached models (#8935)	2025-11-11 03:14:05 -08:00