Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[pull] main from xorbitsai:main #3

Open
wants to merge 617 commits into
base: main
Choose a base branch
from
Open

[pull] main from xorbitsai:main #3

wants to merge 617 commits into from

Conversation

pull[bot]
Copy link

@pull pull bot commented Jan 2, 2024 •
edited
Loading

See Commits and Changes for more details.

Created by pull[bot]

Can you help keep this open source service alive? 💖 Please sponsor : )

@pull pull bot added the ⤵️ pull label Jan 2, 2024
yiboyasss and others added 29 commits July 11, 2024 17:01
@yiboyasss
FIX: [UI] Fix download_hub bugs. (#1846)
ff17be3
@ChengjieLi28
REF: Remove chatglm-cpp and Fix latest llama-cpp-python issue (#1844
0f9c942 
)
@shellc @qinxuye
FEAT: Add support for Flexible Model (#1671)
9bb548a 
Co-authored-by: Xuye (Chris) Qin <[email protected]>
@Zihann73 @ChengjieLi28
BUG: cache status missing for model id with quantization placeholder (#…
e916d05 
…1849)

Co-authored-by: ChengjieLi <[email protected]>
@hainaweiben
ENH: Added the parameter 'worker_ip' to the 'register' model. (#1773)
5e3f254 
Co-authored-by: wuzhaoxin <[email protected]>
@ChengjieLi28
BUG: Fix stream unicode issue for chinese characters when using vllm …
e80910d 
…backend (#1865)
@qinxuye
FEAT: support sd inpainting models (#1879)
1035728
@codingl2k1
FEAT: Stream ChatTTS (#1812)
bd932c5
@qinxuye
ENH: added gguf formats for gemma-2-it (#1874)
4e741cf
@qinxuye
FEAT: support codegeex4 (#1888)
8547c58
@wxiwnd
BUG: sglang stream error while stream_option not set (#1901)
d14e3fd 
Signed-off-by: wxiwnd <[email protected]>
@qinxuye
FEAT: support internlm2.5-chat & internlm2.5-chat-1m (#1887)
35c3008
@amumu96
BUG: fix client import (#1905)
880929c 
Co-authored-by: wuzhaoxin <[email protected]>
@qinxuye
BUG: fix inpainting and flexible infer due to inner API change (#1907)
0a87cfb
@codingl2k1
FEAT: GLM4 support stream tool call (#1876)
2e85c71
@qinxuye
FEAT: support csg-wukong-chat-v0.1 (#1916)
c80f404
@qinxuye
ENH: added MLX for llama-3-instruct, codestral, Yi-1.5-chat, internlm…
a266c8d 
…2.5-chat (#1908)
@Phoenix500526
ENH: add gptq for llama-3-instruct (#1934)
af6dfa3 
Signed-off-by: Phoeniix Zhao <[email protected]>
@yiboyasss
FEAT: [UI]Add configuration for image and audio models. (#1922)
d09c1e9
@qinxuye
FEAT: support mistral-nemo-instruct (#1936)
a0a4d1e
@codingl2k1
FEAT: CosyVoice speech (#1881)
52139c5
@Weaxs @qinxuye
FEAT: add llama-3.1, llama-3.1-instruct (#1932)
2a67d8b 
Co-authored-by: qinxuye <[email protected]>
@qinxuye
FEAT: support mistral-large-instruct (#1944)
c521cdd
@Phoenix500526 @qinxuye
Feat: support for llama 3.1 for vllm (#1935)
681246f 
Co-authored-by: qinxuye <[email protected]>
@qinxuye
DOC: update new models to readme (#1946)
d5562f8
@qinxuye
FEAT: add rembg flexible model to remove background of image (#1917)
aa51ff2
@luweizheng
ENH: Add support of sglang for llama 3 qwen 2 (#1947)
202e6cb
@codingl2k1
BUG: Fix GLM chat (#1966)
94580f6
@qinxuye
REF: enable sglang by default (#1953)
76e3ae5
zjuyzj and others added 30 commits December 11, 2024 20:08
@zjuyzj
ENH: bypass the sampling parameter skip_special_tokens to vLLM backend (
0fd2001 
#2655)
@qinxuye
DOC: add doc about offline usage for SenseVoiceSmall (#2654)
ac9ddca
@yiboyasss
FEAT: [UI] Add a hint for model running. (#2657)
ff92718
@qinxuye
ENH: unify prompt_text as cosyvoice for fish speech (#2658)
dcf3fa8
@qinxuye
FEAT: support VL models for MLX (#2638)
6b0bf6f
@Second222None
FEAT: Add support for CLIP model (#2637)
609b825 
Signed-off-by: Song Wei <[email protected]>
@ChengjieLi28
BUG: stop parameter leads to failure with transformers backend (#…
c6b064b 
…2663)
@codingl2k1
ENH: Update glm4 chat model to new weights (#2660)
f0db4c6
@themanforfree
BUG: fix FishSpeech Negative code found (#2667)
0ba44e5
@qinxuye
FEAT: support llama-3.3-instruct (#2661)
d4f358f
@amumu96
ENH: upgrade sglang in Docker (#2668)
b132fca
@qinxuye
FEAT: support F5-TTS-MLX (#2671)
fffcd93
@wxiwnd
ENH: Guided Decoding OpenAIClient compatibility (#2673)
b0b2fa6 
Signed-off-by: wxiwnd <[email protected]>
@qinxuye
ENH: resample f5-tts-mlx ref audio when sample rate not synching. (#2678
5b1d495 
)
@qinxuye
ENH: support no images for MLX vlm (#2670)
6d1b86a
@codingl2k1
BUG: Fix f5tts audio ref (#2680)
73b2e03
@Timmy-web
FEAT: Support qwen2.5-coder-instruct model for tool calls (#2681)
0ae2727
@codingl2k1
ENH: Update fish speech 1.5 (#2672)
67668a3
@codingl2k1
ENH: Update cosyvoice 2 (#2684)
fb97375
@ChengjieLi28
BUG: glm4-chat cannot apply for continuous batching with transforme…
89ae0d4 
…rs backend (#2695)
@Jun-Howie
FEAT: Support minicpm-4B on vllm (#2697)
5597394 
Co-authored-by: JunHowie <[email protected]>
@hwzhuhao
FEAT: support scheduling-policy for vllm (#2700)
fd52f65
@pengjunfeng11
FEAT: Reduce code redundancy by setting default values (#2711)
ae7b3f6
@Jun-Howie
FEAT: Support QvQ-72B-Preview (#2712)
513af9d 
Co-authored-by: JunHowie <[email protected]>
@qinxuye
FEAT: support SD3.5 series model (#2706)
d342869
@codingl2k1
CHORE: Update new models in readme (#2713)
6213837
@qinxuye
FEAT: support HunyuanVideo (#2721)
267c412
@qinxuye
BUG: adapt mlx-vlm v0.1.7 (#2724)
f5e7f51
@qinxuye
FEAT: support hunyuan-dit text2image (#2727)
dad9307
@hwzhuhao @qinxuye
FEAT: support cline for vllm engine (#2734)
f3ce503 
Co-authored-by: Xuye Qin <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
⤵️ pull
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.