-
-
Notifications
You must be signed in to change notification settings - Fork 182
Pull requests: theroyallab/tabbyAPI
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(templating): default tojson ensure_ascii=False to prevent token bloat
#459
opened Aug 30, 2026 by
Komeiji-Shiki
Loading…
API: Align with llama.cpp output so coding agents work out of the box
#458
opened Aug 29, 2026 by
framp
Loading…
fix(docker): install python3.12-dev so Triton can JIT in the container (#453)
#456
opened Aug 21, 2026 by
Anai-Guo
Contributor
Loading…
API: Report prompt cache and speculative decoding counters in usage stats
#452
opened Aug 19, 2026 by
DenysAshikhin
Loading…
Backends: Read autosplit_reserve for every exllamav3 split mode
#450
opened Aug 15, 2026 by
sashko-zakharchuk
Contributor
Loading…
fix(server): make CORS origins configurable and drop the credentialed wildcard (#448)
#449
opened Aug 14, 2026 by
Anai-Guo
Contributor
Loading…
Ignore HF's generation tags in jinja templates
#437
opened Jul 27, 2026 by
gakada
Contributor
Loading…
fix(model): recognize symlink aliases as the loaded model during inline loading
#436
opened Jul 25, 2026 by
Anai-Guo
Contributor
Loading…
docs(sampling): clarify that sampler override presets resolve from the working directory (#419)
#435
opened Jul 24, 2026 by
Anai-Guo
Contributor
Loading…
[refactor] chore: migrate from
typing.{List,Union,Optional,Dict,Set} to builtin syntax
#394
opened Oct 31, 2025 by
AlpinDale
Member
Loading…
feat: Add XML tool call processing system for GLM-4.5 and Qwen3-Coder models
#378
opened Aug 25, 2025 by
bold84
Contributor
Loading…
Update model.py, to time the model loading time, to create a metric for system tuning to aim for, to optimize the model loading speed
#222
opened Oct 18, 2024 by
awatuna
Loading…
Fix logprobs when multiple tokens are returned at once.
#141
opened Jun 24, 2024 by
zewt
Contributor
Loading…
Added support for multiple API keys, generating OAI-like tokens by default
#99
opened May 1, 2024 by
kir-gadjello
Loading…
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.