feature: add prediction for TPOT #7
Open
+455
−2
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
Wangdai-0800
force-pushed
the
add_tpot
branch
13 times, most recently
from
eef16f8 to
025208d
Compare
doujiang24
reviewed
Nov 20, 2025
pkg/prediction/rls/rls.go
Outdated
| } | ||
|
|
||
| // NewGeneralRLS create RLS instance，dim is the number of varaiant (exclude const) | ||
| func NewGeneralRLS(dim int, forget float64) *RecursiveLeastSquares { |
Contributor
There was a problem hiding this comment.
please do some benchmark, a normal RLS might not be a good performance way, check the ttft prediction way.
Collaborator
Author
There was a problem hiding this comment.
Fixed. Expand the loop and decrease the time cost of Update() by 5 times；
Before:
After:
Wangdai-0800
force-pushed
the
add_tpot
branch
7 times, most recently
from
fe06fd4 to
098012e
Compare
Wangdai-0800
force-pushed
the
add_tpot
branch
from
098012e to
57d1251
Compare
doujiang24
reviewed
Nov 21, 2025
| P[i][i] = 1e6 | ||
| } | ||
| return &TpotRecursiveLeastSquares{ | ||
| dim: TPOT_COEFF_NUM, |
Contributor
There was a problem hiding this comment.
useless? since TPOT_COEFF_NUM is a const
| phi[size-1] = 1.0 | ||
| y := 0.0 | ||
| for i := 0; i < size; i++ { | ||
| y += phi[i] * r.theta[i] |
Contributor
There was a problem hiding this comment.
better to expand this for loop, like the TTFT calculation, for better performance.
| ) | ||
|
|
||
| // TpotPredictor | ||
| type TpotPredictor struct { |
Contributor
There was a problem hiding this comment.
need a interface first, similar to ttft.
| } | ||
|
|
||
| // Predict | ||
| func (c *TpotPredictor) Predict(batchsize, totalTokenNum []uint64) []float64 { |
Contributor
There was a problem hiding this comment.
predict for batch? nope, we just need a single API, similar to ttft prediction.
Predict(batchSize, totalTokenNum uint64) float64
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
No description provided.