William Zhang ca9537e17c [TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264) ... * Why? Prior to this commit, we only supported a single multimodal input for E/P/D disaggregated serving. * What? This commit does a minor refactor of the multimodal embedding handles that cross process boundaries to enable this. Existing unit tests are updated accordingly to test this. The `RequestOutput` has its `mm_embedding_handle` replaced in favor of `disaggregated_params`, addressing a previous TODO. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2026-02-11 20:50:00 -08:00
..
completion_output.yaml	[TRTLLM-1302][feat] Topk logprobs for TRT backend and top1 logprob for PyT backend (#6097)	2025-09-12 15:32:34 +08:00
llm.yaml	[None][chore] set the default value of max_num_tokens explicitly (#8208)	2025-10-14 23:03:02 -07:00
request_output.yaml	[TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264)	2026-02-11 20:50:00 -08:00
sampling_params.yaml	cleanup logprob params (#4039)	2025-05-07 00:50:16 +08:00