Skip to content

Releases: gpustack/gguf-parser-go

v0.13.16

12 Feb 07:27
Compare
Choose a tag to compare
fix: offload clipper to vram0

Signed-off-by: thxCode <[email protected]>

v0.13.15

11 Feb 14:21
Compare
Choose a tag to compare
refactor: estimate partial offloading

Signed-off-by: thxCode <[email protected]>

v0.13.14

10 Feb 12:58
Compare
Choose a tag to compare
refactor: estimate moe

Signed-off-by: thxCode <[email protected]>

v0.13.13

29 Jan 15:27
Compare
Choose a tag to compare
fix: wrong output layer offload at zero ts input

Signed-off-by: thxCode <[email protected]>

v0.13.12

28 Jan 15:45
Compare
Choose a tag to compare
refactor: estimate

Signed-off-by: thxCode <[email protected]>

v0.13.11

16 Jan 08:12
Compare
Choose a tag to compare
docs: readme

Signed-off-by: thxCode <[email protected]>

v0.13.10

15 Jan 13:48
Compare
Choose a tag to compare
fix: calculation error of projector zero offloading

Signed-off-by: thxCode <[email protected]>

v0.13.9

14 Jan 08:12
Compare
Choose a tag to compare
feat: support offloading sd to multi devs

Signed-off-by: thxCode <[email protected]>

v0.13.8

05 Jan 04:16
Compare
Choose a tag to compare
refactor: support qk_m distributable

Signed-off-by: thxCode <[email protected]>

v0.13.7

03 Jan 04:18
Compare
Choose a tag to compare
refactor: estimate

Signed-off-by: thxCode <[email protected]>