github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1292] add 'prompt lookup decoding' for faster inference #667

New Issue
Open
opened 2026-04-12 10:21:22 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 10:21:22 -05:00
Owner
Copy Link

Originally created by @0xdevalias on GitHub (Nov 27, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1292

  • https://github.com/apoorvumang/prompt-lookup-decoding (@apoorvumang)

    • Prompt Lookup Decoding

    • TLDR: We modify speculative decoding where we replace the draft model with simple string matching in the prompt to generate candidate token sequences. This results in significant speedups (2x-4x) in input-grounded tasks, with no effect on output quality. This method can be used with any decoder model without model changes or external datastore, and with both greedy and sampling techniques.

Related Issues:

Originally created by @0xdevalias on GitHub (Nov 27, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1292 - https://github.com/apoorvumang/prompt-lookup-decoding (@apoorvumang) - > Prompt Lookup Decoding - > TLDR: We modify speculative decoding where we replace the draft model with simple string matching in the prompt to generate candidate token sequences. This results in significant speedups (2x-4x) in input-grounded tasks, with no effect on output quality. This method can be used with any decoder model without model changes or external datastore, and with both greedy and sampling techniques. Related Issues: - https://github.com/ggerganov/llama.cpp/issues/4226
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#667
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?