Skip to content

Drop orphan draft references from the external-draft learning-rate note #2978

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
phicksy merged 1 commit into from
Oct 23, 2026
+2 −4
Merged

Drop orphan draft references from the external-draft learning-rate note #2978

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions examples/speculative_decoding/doc/external_draft.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -240,10 +240,8 @@ torchrun --nproc_per_node 8 main.py \
| Epochs | 1 |
| Serving policy | top-k 20, top-p 0.95, temperature 1.0 |

> **Note on the learning rate:** the vocabulary-matched drafts trained against the same dump
> used 1.0e-5 (4B) and 2.0e-6 (0.8B). Each rate was selected by sweeping against held-out
> acceptance; the ordering does not transfer to another target or dump, so re-sweep for your
> own pair.
> **Note on the learning rate:** we recommend sweeping against held-out acceptance to find
> the best rate for your own draft and target.

## Open Items

Expand Down
Loading