-
-
Notifications
You must be signed in to change notification settings - Fork 5.8k
Pull requests: unslothai/unsloth
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(studio): inherit llama_extra_args and honor --no-mmproj
#5902
opened May 31, 2026 by
jimdawdy-hub
Loading…
3 tasks
fix(studio): poll inference status while CLI model is loading
#5901
opened May 31, 2026 by
jimdawdy-hub
Loading…
3 tasks
fix(studio): adopt server-loaded model before chat auto-load
#5900
opened May 31, 2026 by
jimdawdy-hub
Loading…
3 tasks
Studio: fast incremental RAG indexing (warm embedder + FTS5)
#5899
opened May 31, 2026 by
danielhanchen
Member
•
Draft
Fix GRPO full finetuning returning logits instead of hidden states
#5898
opened May 31, 2026 by
danielhanchen
Member
Loading…
Studio: Bypass Permissions (skip confirmation, disable tool sandbox)
#5895
opened May 31, 2026 by
danielhanchen
Member
Loading…
Studio: pin llama-server --threads to physical cores instead of -1
#5894
opened May 31, 2026 by
danielhanchen
Member
Loading…
studio: install macOS llama.cpp prebuilts from the unslothai fork
#5893
opened May 31, 2026 by
danielhanchen
Member
Loading…
chore(deps): bump the cargo-tauri group across 1 directory with 14 updates
dependencies
Pull requests that update a dependency file
rust
Pull requests that update rust code
#5889
opened May 31, 2026 by
dependabot
Bot
Loading…
chore(deps): bump tauri from 2.10.3 to 2.11.1 in /studio/src-tauri in the cargo-tauri-security group across 1 directory
dependencies
Pull requests that update a dependency file
rust
Pull requests that update rust code
#5888
opened May 31, 2026 by
dependabot
Bot
Loading…
Studio: fall back to a tokenless release redirect when the llama.cpp REST API is rate limited
#5886
opened May 31, 2026 by
danielhanchen
Member
Loading…
fix: bump Tauri to 2.11.1 in Studio src-tauri (CVE-2026-42184)
#5885
opened May 31, 2026 by
danielhanchen
Member
Loading…
Fix full finetuning precision on V100 / no-bf16 GPUs
#5880
opened May 31, 2026 by
danielhanchen
Member
Loading…
Keep V100 (Volta) GPUs on cu128 instead of cu130
#5876
opened May 31, 2026 by
danielhanchen
Member
Loading…
Studio: refine tool call and reasoning trigger UI
#5873
opened May 30, 2026 by
shimmyshimmer
Member
Loading…
Studio: fix chat preset persistence with fast mode
#5870
opened May 29, 2026 by
Imagineer99
Collaborator
Loading…
Studio: Add inline confirmation (Allow/Always allow/Deny) for tool calls
#5869
opened May 29, 2026 by
oobabooga
Contributor
Loading…
Studio: fix mobile composer action overflow
#5868
opened May 29, 2026 by
Imagineer99
Collaborator
•
Draft
Studio: reject silently CPU-only llama-server (validate GPU offload)
#5858
opened May 29, 2026 by
danielhanchen
Member
Loading…
Studio: account for mmproj VRAM in GGUF fit budget (#5825)
#5849
opened May 29, 2026 by
hoobnn
Loading…
fix: complete truncated _hf_hub_cache_dir function (closes #4812)
#5843
opened May 28, 2026 by
botbikamordehai2-sketch
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.