Skip to content

Eagle speculative decoding part 3: small modifications to the general scheduler#2709

Merged
merrymercy merged 95 commits intomainfrom
pr-lianmin-spec
Jan 2, 2025
Merged

Eagle speculative decoding part 3: small modifications to the general scheduler#2709
merrymercy merged 95 commits intomainfrom
pr-lianmin-spec

Conversation

@merrymercy
Copy link
Copy Markdown
Contributor

@merrymercy merrymercy commented Jan 2, 2025

This is used for speculative decoding in #2150. It includes all small modifications to the general scheduler.

Co-authored-by: yukavio <kavioyu@gmail.com>

@merrymercy merrymercy changed the title Eagle speculative decoding part 3: small modifications for the scheduler Eagle speculative decoding part 3: general small modifications for the scheduler Jan 2, 2025
@merrymercy merrymercy changed the title Eagle speculative decoding part 3: general small modifications for the scheduler Eagle speculative decoding part 3: small modifications to the general scheduler Jan 2, 2025
Comment thread python/sglang/srt/server_args.py
@merrymercy merrymercy merged commit ad20b79 into main Jan 2, 2025
@merrymercy merrymercy deleted the pr-lianmin-spec branch January 2, 2025 10:09
XiaotongJiang pushed a commit to XiaotongJiang/sglang that referenced this pull request Jan 3, 2025
… scheduler (sgl-project#2709)

Co-authored-by: kavioyu <kavioyu@tencent.com>
timethink pushed a commit to timethink/sglang that referenced this pull request Mar 9, 2025
… scheduler (sgl-project#2709)

Co-authored-by: kavioyu <kavioyu@tencent.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.

2 participants