23.05.18

fix: fastchat t5 model extra space (#49)

* fix: fastchat t5 model extra space

Signed-off-by: Keming <kemingyang@tensorchord.ai>

* fix

Signed-off-by: Keming <kemingyang@tensorchord.ai>

* fix token statistic

Signed-off-by: Keming <kemingyang@tensorchord.ai>

---------

Signed-off-by: Keming <kemingyang@tensorchord.ai>

23.05.14

What's Changed

• feat: Add low cpu by default by @gaocegege in #40
• chore: Update readme by @gaocegege in #41
• feat: add cpu optional deps by @kemingy in #43

Full Changelog: 23.05.13...23.05.14

23.05.9

chore: Add vicuna (#28)

Signed-off-by: Ce Gao <cegao@tensorchord.ai>

23.05.8

chore: Disbale warmup in llama (#27)

Signed-off-by: Ce Gao <cegao@tensorchord.ai>

23.05.7

chore: Use int8 instead of hf (#26)

Signed-off-by: Ce Gao <cegao@tensorchord.ai>

23.05.13: fix: add gpu & cpu optional deps (#39)

Signed-off-by: Keming <kemingyang@tensorchord.ai>

23.05.12: feat: add CLI and package (#37)

* feat: add CLI and package

Signed-off-by: Keming <kemingyang@tensorchord.ai>

* fix lint

Signed-off-by: Keming <kemingyang@tensorchord.ai>

* add dry run image name

Signed-off-by: Keming <kemingyang@tensorchord.ai>

---------

Signed-off-by: Keming <kemingyang@tensorchord.ai>

23.05.11

What's Changed

• chore: Update README and make format by @gaocegege in #33
• add embedding support in main.py by @tddschn in #22
• fix: embedding endpoints by @kemingy in #34

New Contributors

• @tddschn made their first contribution in #22

Full Changelog: 23.05.10...23.05.11

23.05.10

chore: Add chatglm 6b (#32)

Signed-off-by: Ce Gao <cegao@tensorchord.ai>

23.05.6

fix: Fix dir typo (#25)

Signed-off-by: Ce Gao <cegao@tensorchord.ai>