kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-13 22:18:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[None][fix] revert https://github.com/NVIDIA/TensorRT-LLM/pull/10445. (#10547)

Browse Source 
Signed-off-by: Yuxian Qiu <142763828+yuxianq@users.noreply.github.com>
This commit is contained in:
Yuxian Qiu 2026-01-09 10:50:04 +08:00 committed by GitHub
parent 56e779d09f
commit afa55c12b6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 0 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tensorrt_llm/_torch/models/modeling_speculative.py
View File

@ -953,14 +953,6 @@ class SpecDecOneEngineForCausalLM(DecoderModelForCausalLM[TModel, TConfig],
hidden_states = hidden_states[:attn_metadata.num_tokens]
if self.draft_model is not None:
# For one-model speculative decoding with PP, only the last PP rank
# has valid hidden_states from the target model. The spec_worker (which
# runs the draft model loop) should only run on the last PP rank.
# Non-last PP ranks return None and let the PP sync handle the results.
mapping = self.model.model_config.mapping
if mapping.has_pp() and not mapping.is_last_pp_rank():
return None
# get logits
logits = self.logits_processor.forward(
hidden_states[spec_metadata.gather_ids],