Skip to content

Releases: gpustack/llama-box

v0.0.28

08 Aug 05:02
Compare
Choose a tag to compare
chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.27

07 Aug 01:03
Compare
Choose a tag to compare
refactor: lock only one slot for embedding at pooling

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.26

06 Aug 12:17
Compare
Choose a tag to compare
fix: cmake

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.25

06 Aug 08:32
Compare
Choose a tag to compare
chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.24

05 Aug 14:07
Compare
Choose a tag to compare
chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.23

02 Aug 07:27
Compare
Choose a tag to compare
chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.22

31 Jul 17:02
Compare
Choose a tag to compare
feat: distinguish embedding-only model

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.21

30 Jul 11:01
7531004
Compare
Choose a tag to compare
fix: build musa (#4)

* Revert "revert: "feat: support musa""

This reverts commit 775680409df4e9950f4cada1c39bf1d48943824d.

* fix: build musa

Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>

* Switch C/CXX to clang/clang++ for building MUSA target

Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>

---------

Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>

v0.0.20

29 Jul 07:16
Compare
Choose a tag to compare
fix: embedding

Signed-off-by: thxCode <thxcode0824@gmail.com>

v0.0.19

28 Jul 13:07
Compare
Choose a tag to compare
chore: bump llama.cpp

Signed-off-by: thxCode <thxcode0824@gmail.com>