507a9d937b
Release 0.5.5
...
http-api-bindings@0.5.5
llama-cpp-bindings@0.5.5
tabby@0.5.5
tabby-common@0.5.5
tabby-download@0.5.5
tabby-inference@0.5.5
tabby-scheduler@0.5.5
Generated by cargo-workspaces
2023-11-09 00:26:12 -08:00
16f47005dd
fix: llama.cpp queuing logic
2023-11-09 00:25:31 -08:00
732f022708
Release 0.5.4
...
http-api-bindings@0.5.4
llama-cpp-bindings@0.5.4
tabby@0.5.4
tabby-common@0.5.4
tabby-download@0.5.4
tabby-inference@0.5.4
tabby-scheduler@0.5.4
Generated by cargo-workspaces
2023-11-07 13:12:33 -08:00
f72b87bf79
fix: deadlock between background job and requests ( #720 )
...
* fix: deadlock between background job and requests
* refactor: extract LlamaService
2023-11-07 13:12:13 -08:00
8046a482ea
Release 0.5.3
...
http-api-bindings@0.5.3
llama-cpp-bindings@0.5.3
tabby@0.5.3
tabby-common@0.5.3
tabby-download@0.5.3
tabby-inference@0.5.3
tabby-scheduler@0.5.3
Generated by cargo-workspaces
2023-11-07 00:57:48 -08:00
277528d01c
fix: cuda serialization
2023-11-07 00:57:11 -08:00
0226a379de
Release 0.5.2
...
http-api-bindings@0.5.2
llama-cpp-bindings@0.5.2
tabby@0.5.2
tabby-common@0.5.2
tabby-download@0.5.2
tabby-inference@0.5.2
tabby-scheduler@0.5.2
Generated by cargo-workspaces
2023-11-07 00:30:51 -08:00
551d1dc0ba
Release 0.5.2-rc.0
...
http-api-bindings@0.5.2-rc.0
llama-cpp-bindings@0.5.2-rc.0
tabby@0.5.2-rc.0
tabby-common@0.5.2-rc.0
tabby-download@0.5.2-rc.0
tabby-inference@0.5.2-rc.0
tabby-scheduler@0.5.2-rc.0
Generated by cargo-workspaces
2023-11-06 23:03:14 -08:00
c28f5838ce
fix: support cpu only run in llama.cpp cuda build
2023-11-06 23:02:31 -08:00
e87e78b74c
fix: llama.cpp requires kv cache to be N_CTX * parallelism ( #714 )
2023-11-06 23:02:28 -08:00
7ca3221b52
fix: when there's an error happens in background inference loop, it should exit the process ( #713 )
2023-11-06 23:02:23 -08:00
03a9c7dac3
chore: add machete check to ensure no unused dependencies ( #701 )
...
* refactor: remove useless dependencies
* add machete
2023-11-06 23:02:12 -08:00
b4fe249636
feat: support downloading resume ( #700 )
2023-11-04 20:12:18 -07:00
36d13d2837
fix(llama.cpp): wrongly index for n_seq in warmup
2023-11-04 20:12:13 -07:00
01ce18fe1a
fix: llama.cpp warmp logic
2023-11-04 20:12:09 -07:00
0b6108dfc2
chore: up ci.yml to mac-latest
2023-11-04 20:12:00 -07:00
536c7e86a0
Release 0.5.0
...
http-api-bindings@0.5.0
llama-cpp-bindings@0.5.0
tabby@0.5.0
tabby-common@0.5.0
tabby-download@0.5.0
tabby-inference@0.5.0
tabby-scheduler@0.5.0
Generated by cargo-workspaces
2023-11-03 18:00:38 -07:00
281d189848
Release 0.5.0-rc.4
...
http-api-bindings@0.5.0-rc.4
llama-cpp-bindings@0.5.0-rc.4
tabby@0.5.0-rc.4
tabby-common@0.5.0-rc.4
tabby-download@0.5.0-rc.4
tabby-inference@0.5.0-rc.4
tabby-scheduler@0.5.0-rc.4
Generated by cargo-workspaces
2023-11-03 17:36:51 -07:00
c21ea483f4
fix: collect_snippet should handle NotReady error
2023-11-03 17:35:06 -07:00
3df3ad4f60
docs: update change log and docs
2023-11-03 14:05:04 -07:00
03fe1e9f6b
Release 0.5.0-rc.3
...
http-api-bindings@0.5.0-rc.3
llama-cpp-bindings@0.5.0-rc.3
tabby@0.5.0-rc.3
tabby-common@0.5.0-rc.3
tabby-download@0.5.0-rc.3
tabby-inference@0.5.0-rc.3
tabby-scheduler@0.5.0-rc.3
Generated by cargo-workspaces
2023-11-03 13:53:31 -07:00
1b92d5eabc
fix: handlebar syntax in meta action
2023-11-03 13:53:09 -07:00
a5bb20becb
Release 0.5.0-rc.2
...
http-api-bindings@0.5.0-rc.2
llama-cpp-bindings@0.5.0-rc.2
tabby@0.5.0-rc.2
tabby-common@0.5.0-rc.2
tabby-download@0.5.0-rc.2
tabby-inference@0.5.0-rc.2
tabby-scheduler@0.5.0-rc.2
Generated by cargo-workspaces
2023-11-03 13:26:51 -07:00
bddcedc1a5
fix: handlebar syntax in meta action
2023-11-03 13:26:28 -07:00
f97cdf2ad9
Release 0.5.0-rc.1
...
http-api-bindings@0.5.0-rc.1
llama-cpp-bindings@0.5.0-rc.1
tabby@0.5.0-rc.1
tabby-common@0.5.0-rc.1
tabby-download@0.5.0-rc.1
tabby-inference@0.5.0-rc.1
tabby-scheduler@0.5.0-rc.1
Generated by cargo-workspaces
2023-11-03 13:23:25 -07:00
01b95de8a1
fix: docker branch tag should only generate when not empty
2023-11-03 13:23:02 -07:00
61605ca553
Release 0.5.0-rc.0
...
http-api-bindings@0.5.0-rc.0
llama-cpp-bindings@0.5.0-rc.0
tabby@0.5.0-rc.0
tabby-common@0.5.0-rc.0
tabby-download@0.5.0-rc.0
tabby-inference@0.5.0-rc.0
tabby-scheduler@0.5.0-rc.0
Generated by cargo-workspaces
2023-11-03 11:35:26 -07:00
e4efcc4091
fix: avoid special keywords (e.g AND) failed the query parsing ( #695 )
2023-11-03 01:13:28 +00:00
2adcc0726c
feat: support prefix query on name field ( #694 )
...
* feat: support prefix phase query on name field
* update changelog
2023-11-03 01:04:33 +00:00
acb3a33d78
fix: handle non utf-8 / utf-16 error
2023-11-02 16:29:30 -07:00
eb34850a5e
fix: output err if step failed
2023-11-02 16:15:11 -07:00
4c7eae584e
feat: add model warmup logic ( #693 )
2023-11-02 23:07:32 +00:00
0e4a2d2a12
feat: simplify download management, model file should be able to indi… ( #690 )
...
* feat: simplify download management, model file should be able to individually introduced
* fix typo
* update local model support
* update spec back
* update spec
* update
* update
2023-11-02 16:01:04 -07:00
0ed4289958
chore: only run release-binary on non PR
2023-11-01 23:06:25 -07:00
90e446bfba
docs: Update MODEL_SPEC.md
2023-11-01 09:37:38 -07:00
36ffeb63f1
refactor: remove useless rust-cxx-cmake-bridge
2023-10-31 17:58:21 -07:00
296342efd8
refactor: use llama.cpp tokenizer ( #683 )
...
* refactor: switch to llama.cpp tokenizer to simplify implementation
* refactor: remove tokenizer dependency from tabby
* refactor: renaming decoding to stop condition
* refactor: remove tokenizer dependency
* refactor: remove submodule
* chore: update formatting
* move tokenization to c++
2023-10-31 22:16:09 +00:00
f15926f233
chore(ui): update crates/tabby/ui
2023-10-31 08:51:22 -07:00
177689341f
chore(ui): rename runners to workers ( #681 )
2023-10-30 22:11:01 -07:00
3f1f8bfd30
fix: add /swagger to tabby ui handler
2023-10-30 17:36:22 -07:00
73758e207d
feat: improve dashboard UI ( #677 )
2023-10-30 21:47:38 +00:00
b4772fbcd0
feat(ui): add dashboard ( #674 )
...
* feat(ui): add dashboard
* handle path
2023-10-30 07:29:50 +00:00
89a63dbf33
fix: when send failed, treat the request as stopped ( #673 )
2023-10-30 06:27:09 +00:00
de827b1e74
Revert "feat: make --model optional ( #668 )" ( #672 )
...
This reverts commit c55e4481ba
2023-10-29 21:44:11 -07:00
f991b8b7ab
fix(agent): update config.toml template. ( #671 )
2023-10-29 21:27:28 -07:00
e88097320b
feat(agent): add auth token config. ( #649 )
...
* feat(agent): add auth token config.
* fix: fix agent loading auth token.
* fix: update retain old config filepath.
* fix: update retain old config filepath.
* fix: lint.
* fix: remove auto migrate, update config template.
2023-10-29 21:09:18 -07:00
c51e00ee45
feat(agent): add experimental option: scope of indentation filter. ( #652 )
...
* feat(agent): add experimental option: scope of indentation filter.
* fix: add config to fix unit test for limitScopeByIndentation.
2023-10-29 19:59:09 -07:00
238d81ad4f
feat(agent): add experimental option: strip auto-closing chars in prompt suffix. ( #651 )
...
* feat(agent): add experimental option: strip auto-closing chars in prompt suffix.
* fix: rename settings adding experimental prefix.
2023-10-29 19:58:25 -07:00
b47bdd5d77
fix: align with fastchat mainstream ( #670 )
...
Fastchat mainstream change its return format, and text now is only
string in choices structure.
So make this change, to work with mainstream fastchat.
Signed-off-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Lei Wen <wenlei03@qiyi.com>
2023-10-29 19:31:46 -07:00
88d2617a34
fix: move events writer to individual thread ( #669 )
2023-10-30 01:31:41 +00:00
Meng Zhang