26fedf6bef
update fire_red_vad
2026-04-16 19:47:28 +08:00
f901f4cbfe
add FireRedVAD
2026-04-15 17:42:41 +08:00
3e30360998
fix LiquidAI/LFM2.5-VL-450M chat_template load bug
2026-04-10 23:06:09 +08:00
527fd359f8
update fmt
2026-04-08 19:21:20 +08:00
34cd60d9ce
update voxcpm instuction
2026-04-08 19:18:44 +08:00
adf31dc16f
add VoxCPM2
2026-04-08 18:55:03 +08:00
110a1bc5eb
Merge branch 'pr/happynewplay/41'
2026-04-06 18:23:23 +08:00
ed4811a01f
add qwen3-reranker
2026-04-06 17:48:15 +08:00
7142e712f2
add qwen3-embedding and all-minilm-l6-v2
2026-04-06 15:35:49 +08:00
44d91da650
CLI update: subcommand must be specified
2026-04-03 20:43:51 +08:00
279480e3d7
generate add penalty repeat
2026-04-03 14:15:10 +08:00
bd8eee6520
refactor generate code
2026-04-02 22:22:52 +08:00
b254d21efc
refactor deepseek_ocr/fun_asr_nano generate code
2026-04-01 19:11:10 +08:00
741869d6dd
update WhichModel enum
2026-03-31 18:45:01 +08:00
3e510a4172
dependencies delete aha_openai_dive,chrono
2026-03-31 12:30:12 +08:00
363833d8fb
delete some code
2026-03-30 20:36:57 +08:00
ccbe799b90
update model_name
2026-03-30 20:33:48 +08:00
ea78da7834
add LFM2.5-VL-1.6B|LFM2-VL-1.6B
2026-03-30 00:44:41 +08:00
b881dfcd8d
add lfm2vl
2026-03-27 11:16:31 +08:00
aec47e47af
给 glm-ocr 添加 gguf 和 onnx 格式推理
2026-03-26 17:42:58 +08:00
b6b970fd25
添加 All-MiniLM-L6-v2-Embedding 模型
2026-03-26 13:40:24 +08:00
a74b67c93f
主要改了 vendor/esaxx-rs/build.rs：只在 crt-static 目标下才启用 static_crt(true)，用来修复 Windows 下常见的 MSVC 运行库冲突
2026-03-25 16:05:00 +08:00
b8d8732c3d
添加 rerank 和 embedding模型支持,并且添加 onnx 模型
2026-03-24 16:18:39 +08:00
7d3cd50e35
update fmt
2026-03-23 22:09:20 +08:00
9224593b78
add LFM2-1.2B, LFM2.5-1.2B-Instruct
2026-03-23 22:07:41 +08:00
6890f86030
add deepseek-ocr2 support
2026-03-18 19:15:21 +08:00
55a5007c07
add PaddleOCR-VL1.5 support
2026-03-17 21:30:50 +08:00
fb4a50f745
cli add about gguf param
2026-03-17 15:39:34 +08:00
80d36b5308
add Qwen3.5 mmproj gguf
2026-03-16 14:50:59 +08:00
21caee0522
update fmt
2026-03-14 20:06:20 +08:00
aad0e62151
add qwen3.5 gguf
2026-03-14 19:27:01 +08:00
4d544ab68f
from gguf build chat_template and tokenizer
2026-03-11 17:30:28 +08:00
20b5260633
update fmt
2026-03-07 18:09:29 +08:00
d2524d6a19
merge glm-ocr model
2026-03-07 18:08:06 +08:00
cf308f93eb
Merge branch 'pr/jasonzou/31'
2026-03-07 14:25:44 +08:00
1fe06110ff
more glm-ocr tweaks
2026-03-06 11:25:44 -05:00
2ef86b5a88
generate remove unnecessary code
2026-03-06 19:40:39 +08:00
037207eccd
update generate param init
2026-03-06 19:08:58 +08:00
548eb8185e
usage add prompt_tokens
2026-03-06 18:38:16 +08:00
3156818a0c
glm-ocr
2026-03-05 23:49:49 -05:00
9a09b998a6
fix qwen3.5-9b config bug
2026-03-06 12:31:00 +08:00
f482bf1a54
update qwen3.5 only text conpute pos bug
2026-03-06 12:14:18 +08:00
b2a687a05e
update fmt
2026-03-05 21:59:38 +08:00
4ae8b0b2f4
add Qwen3.5 model
2026-03-05 21:57:03 +08:00
a61b899741
update interpolate
2026-03-01 12:44:14 +08:00
28f8fb6c1b
update fmt
2026-02-14 16:34:12 +08:00
b77676f029
delete index-ttss
2026-02-14 16:06:50 +08:00
2c34fc2d79
updata index tts
2026-02-14 15:52:30 +08:00
390d916ea6
feat(api): add health check and models endpoints with documentation
...
- Add /health endpoint to check service status for orchestration systems
- Add /models endpoint with OpenAI API compatible format
- Document new endpoints in both English and Chinese API docs
- Include example usage and response formats in documentation
- Add comprehensive test coverage for health and models endpoints
- Refactor model storage to include type information alongside instance
- Move model ID and type methods to WhichModel implementation
- Update API calls to access model instance through stored wrapper
2026-02-08 12:10:40 +08:00
38ea72e407
refactor: reorganize imports and improve code formatting across multiple modules
2026-02-08 11:07:53 +08:00
jhqxxx
273265088@qq.com
jason
jason
XiaoYang