Skip to content

Releases: gpustack/gpustack-higress-plugin

release-20260224-172837

24 Feb 09:29

Choose a tag to compare

fix: the non-streaming requests are judged as streaming requests

As the content-length header is removed by other plugin, use the content-type header to determine the data type

release-20251230-174029

30 Dec 09:41

Choose a tag to compare

fix: append chunk even if the usage exists but it is nil

release-20251226-191631

26 Dec 11:17

Choose a tag to compare

fix: refactor the streaming logic

Should consider the frame has incomplete json.
Assumble the chunk into a valid json before check the usage because the usage key might
be split into usa and ge, then we can't determine the right usage from data.

release-20251226-120212

26 Dec 04:03

Choose a tag to compare

fix: only process the target usage chunk only

If a frame has multiple chunk data which usage chunk is in the middle, should ignore the other chunk.

release-20251224-224846

24 Dec 14:49

Choose a tag to compare

fix: usage doesn't set correctly in mindIE upstream

If a large usage response is sent to onStreamingResponseBody function,
it will be seperated into multiple frame. It needs to be assembled into a valid json
before modifying the usage data.

release-20251218-225148

18 Dec 14:53

Choose a tag to compare

fix: missing data: prefix for non usage chunk

release-20251122-232059

22 Nov 15:22

Choose a tag to compare

fix: TPOT calculates more accurately

release-20251119-154204

19 Nov 07:43

Choose a tag to compare

fix: compatible with non-streaming request

release-20251111-153636

11 Nov 07:37

Choose a tag to compare

fix: only includes chat/completions and completions paths

release-20251111-013025

10 Nov 17:31

Choose a tag to compare

fix: tpot needs to be stored in float64 format and retain 2 decimal p…