fix: [TRTLLM+ LLAMA4 + Eagle 3] Remove the ‘two-models config’ and set the ‘one-model’ solution as the default, #2660
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
richardhuo-nv
force-pushed
the
rihuo/fix_eagle_config
branch
3 times, most recently
from
151b5b6 to
b1cd2ae
Compare
richardhuo-nv
requested review from
KrishnanPrash,
rmccorm4 and
tanmayv25
and removed request for
KrishnanPrash and
tanmayv25
richardhuo-nv
force-pushed
the
rihuo/fix_eagle_config
branch
2 times, most recently
from
0d168c5 to
91285c7
Compare
fix name Signed-off-by: richardhuo-nv <rihuo@nvidia.com> sign
richardhuo-nv
force-pushed
the
rihuo/fix_eagle_config
branch
from
91285c7 to
6851193
Compare
tanmayv25
approved these changes
Aug 22, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Overview:
The "two models" eagle solution became very unstable in Trtllm 1.0.0rc6 and TRTLLM team seems is not going to maintain it in a longer term.
Cherry-pick for #2661
Details:
Remove the ‘two-models config’ and set the ‘one-model’ solution as the default, since whether one or two models are used is purely an implementation detail, they are both just Eagle speculative decoding.
Where should the reviewer start?
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)