Skip to content

add speculative decoding#71

Merged
skyzh merged 2 commits intomainfrom
skyzh/speculative
Sep 26, 2025
Merged

add speculative decoding#71
skyzh merged 2 commits intomainfrom
skyzh/speculative

Conversation

@skyzh
Copy link
Copy Markdown
Owner

@skyzh skyzh commented Sep 26, 2025

pdm run main --solution ref --loader week2 --model qwen2-7b --draft-model qwen2-0.5b

for most of the times it can decode 4 tokens at a time

Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
@skyzh skyzh merged commit ad6d976 into main Sep 26, 2025
2 checks passed
@skyzh skyzh deleted the skyzh/speculative branch September 26, 2025 05:30
jinhuix pushed a commit to jinhuix/tiny-llm that referenced this pull request Oct 10, 2025
* add speculative decoding

Signed-off-by: Alex Chi Z <iskyzh@gmail.com>

* update readme

Signed-off-by: Alex Chi Z <iskyzh@gmail.com>

---------

Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant