Skip to content

Pull requests: xorbitsai/inference

New pull request New
30 Open 2,117 Closed
30 Open 2,117 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

feat(core): add model loading state machine to prevent routing to loading models feature
#5032 opened Jun 15, 2026 by m199369309 Collaborator Loading…
8 tasks
v2.x
5
fix(worker): strip test envs before recover and clean up GPU orphans bug Something isn't working gpu
#5031 opened Jun 15, 2026 by m199369309 Collaborator Loading…
2 of 7 tasks
v2.x
10
fix(vllm): force spawn for single-GPU EngineCore and fix health check scheduling bug Something isn't working gpu
#5030 opened Jun 15, 2026 by m199369309 Collaborator Loading…
5 of 6 tasks
v2.x
4
feat: add Tencent Hy-MT2 series support feature
#5029 opened Jun 15, 2026 by xiaoyesoso Contributor Loading… v2.x
5
feat: gate model remote-code execution behind a config switch feature
#5027 opened Jun 13, 2026 by qxyuan853 Loading… v2.x
10
feat(vllm): support glm5 tool parser feature
#5019 opened Jun 12, 2026 by llyycchhee Collaborator Loading… v2.x
14
Draft: parse tool_calls arguments
#4921 opened May 18, 2026 by la1ty Contributor Loading… v2.x
1
10
feat: batch text-only MLX VLM requests feature
#4918 opened May 16, 2026 by qinxuye Contributor Loading… v2.x
8
fix: include user-defined LLM families in _resolve_architectures bug Something isn't working
#4860 opened Apr 27, 2026 by Ricardo-M-L Contributor Loading… v2.x
12
ENH: update model "gpt-oss" JSON enhancement New feature or request
#4501 opened Jan 16, 2026 by OliverBryant Collaborator Loading… v2.x
BUG: MLX distributed error with vscode cline bug Something isn't working
#4379 opened Dec 17, 2025 by OliverBryant Collaborator Loading… v2.x
1
BUG: worker dead with xoscar v0.8.0 bug Something isn't working
#4363 opened Dec 15, 2025 by OliverBryant Collaborator Loading… v2.x
1
FEAT: mistral-small-3.2-instruct model support feature
#3820 opened Jul 21, 2025 by llyycchhee Collaborator Loading… v2.x
FEAT: [UI] implement step-by-step user onboarding. feature
#3530 opened May 27, 2025 by yiboyasss Contributor Loading… v2.x
1
FEAT: Kimi-VL-A3B feature
#3372 opened May 2, 2025 by Minamiyama Collaborator • Draft v2.x
6
FEAT: jina-reranker-m0 feature
#3209 opened Apr 9, 2025 by Minamiyama Collaborator • Draft v2.x
1
FEAT: new model mPLUG-Owl3 feature
#3199 opened Apr 7, 2025 by Minamiyama Collaborator • Draft v2.x
1
FEAT: bge vl embedding series feature
#3092 opened Mar 19, 2025 by Minamiyama Collaborator • Draft v2.x
1
UI: github in model card, and open in new
#2923 opened Feb 23, 2025 by Minamiyama Collaborator Loading… v2.x
ENH: cosyvoice support pt file enhancement New feature or request
#2431 opened Oct 12, 2024 by Minamiyama Collaborator Loading… v2.x
9
REF: load model card json refactor
#2246 opened Sep 7, 2024 by Minamiyama Collaborator Loading… v2.x
BUG: Fix ChatTTS stream bug Something isn't working
#2101 opened Aug 16, 2024 by codingl2k1 Contributor • Draft v2.x
FEAT: Initially support OpenVINO feature
#1677 opened Jun 20, 2024 by qinxuye Contributor Loading… v2.x
FEAT: Code completions feature
#1476 opened May 11, 2024 by mikeshi80 Contributor Loading… v2.x
1
ENH: Added the check for reserved model uid like "instances", "prompts" etc. enhancement New feature or request
#1303 opened Apr 15, 2024 by mikeshi80 Contributor Loading… v2.x
ProTip! Exclude everything labeled bug with -label:bug.