llama.cpp
TP: quantized KV cache support
#23792
Merged

TP: quantized KV cache support #23792

JohannesGaessler
JohannesGaessler JohannesGaessler requested a review from CISC CISC 9 days ago
JohannesGaessler JohannesGaessler requested a review from ggerganov ggerganov 9 days ago
github-actions github-actions added ggml
nifgraup
JohannesGaessler
CISC
JohannesGaessler
krampenschiesser
Stoney49th
cb88
JohannesGaessler JohannesGaessler force pushed from 2b2d0e2c to 5c26ac50 7 days ago
JohannesGaessler TP: quantized KV cache support
5c7f3f79
JohannesGaessler fix partial view
a4304065
JohannesGaessler remove overly strict assert
ae22953f
JohannesGaessler JohannesGaessler force pushed from 5c26ac50 to ae22953f 7 days ago
JohannesGaessler
gordan-bobic
Stoney49th
JohannesGaessler
Stoney49th
CISC
CISC approved these changes on 2026-05-30
ggerganov
ggerganov approved these changes on 2026-06-01
JohannesGaessler JohannesGaessler merged 8e6fff84 into master 5 days ago
joeldeteves
wx33398-ctrl
gdyxml2000
gordan-bobic
tooltd

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone