llama.cpp
CUDA: improve top-k algorithm selection
#28713
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
15
Changes
View On
GitHub
CUDA: improve top-k algorithm selection
#28713
ORippler
merged 15 commits into
ggml-org:master
from
praneshgo:pgonegandla/topk-radix-only
CUDA: radix top-k for large row counts
a011ccd3
github-actions
added
ggml
github-actions
added
CUDA
praneshgo
marked this pull request as ready for review
59 days ago
praneshgo
requested a review
59 days ago
ynankani
commented on 2026-09-22
ORippler
closed this
53 days ago
ynankani
reopened this
46 days ago
praneshgo
marked this pull request as draft
46 days ago
Merge branch 'master' into pgonegandla/topk-radix-only
04e682a2
CUDA: select the TOP_K implementation by shape
e4683d84
CUDA: make top-k comments less verbose
0d4ee054
praneshgo
changed the title
CUDA: radix top-k for large row counts
CUDA: improve top-k algorithm selection
45 days ago
github-actions
added
testing
praneshgo
marked this pull request as ready for review
44 days ago
praneshgo
requested a review
from
ggerganov
44 days ago
praneshgo
requested a review
from
ynankani
44 days ago
gaugarg-nv
requested changes on 2026-10-07
CUDA: remove the TOP_K width limit from supports_op
cb688931
CUDA: use DeviceTopK for single-row TOP_K if available
975bf810
praneshgo
requested a review
from
gaugarg-nv
43 days ago
ORippler
commented on 2026-10-07
CUDA: avoid ncols overflow in the TOP_K bitonic check
d2f31e40
CUDA: share the row chunking helper between argsort and top-k
036b9f4c
praneshgo
requested a review
from
ORippler
43 days ago
ORippler
requested changes on 2026-10-08
CUDA: do the TOP_K radix blocks_per_row math in int64_t
61c36829
CUDA: rename GGML_CUDA_TOP_K_NROWS_THRESHOLD_DEVICETOPK to GGML_CUDA_…
0454fc41
CUDA: share one sort helper between the bitonic and CUB TOP_K paths
8fb941ac
CUDA: update the TOP_K TODO, threshold and chunking comments
4bdba64a
tests: add TOP_K cases that span several row chunks
ebcdb647
gaugarg-nv
approved these changes on 2026-10-08
ORippler
commented on 2026-10-08
CUDA: use int64_t col in the TOP_K radix loops, fix threshold comment
a406e45b
am17an
approved these changes on 2026-10-08
CUDA: limit TOP_K and ARGSORT support to ne[0] <= INT_MAX
45211ef7
praneshgo
requested a review
from
ORippler
42 days ago
ORippler
approved these changes on 2026-10-08
ORippler
merged
71ad0590
into master
42 days ago
Login to write a write a comment.
Login via GitHub
Reviewers
ORippler
am17an
gaugarg-nv
ynankani
ggerganov
Assignees
No one assigned
Labels
testing
ggml
CUDA
Milestone
No milestone
Login to write a write a comment.
Login via GitHub