ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
unsloth/studio/backend
History
Nilay 59bda2e1f7
 Studio: reuse MLX prompt cache across turns instead of re-prefilling (#7311) 
* Studio: reuse MLX prompt cache across turns instead of re-prefilling

* clean up

* key prompt cache on what the KV covers

* skip windowed KV caches past their window

* verify prefix coverage before caching KV
2026-07-22 02:35:33 -07:00
..
assets Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
auth Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
core Studio: reuse MLX prompt cache across turns instead of re-prefilling (#7311) 2026-07-22 02:35:33 -07:00
hub Feat/model picker per model config v2 (#7207) 2026-07-20 22:53:22 -07:00
loggers Studio: quiet noisy logs, log real progress, and speed up Windows/macOS dataset prep (#7087) 2026-07-15 06:49:52 -07:00
models Fix resume training crash recovery and MLX checkpoints (#6796) 2026-07-21 02:34:58 -07:00
picker Feat/model picker per model config v2 (#7207) 2026-07-20 22:53:22 -07:00
plugins Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
requirements Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
routes Fix resume training crash recovery and MLX checkpoints (#6796) 2026-07-21 02:34:58 -07:00
state Studio: shareable per-checkpoint preview links (#6486) 2026-06-24 06:31:53 -07:00
storage Fix resume training crash recovery and MLX checkpoints (#6796) 2026-07-21 02:34:58 -07:00
tests Studio: reuse MLX prompt cache across turns instead of re-prefilling (#7311) 2026-07-22 02:35:33 -07:00
utils Studio: fix loading split GGUFs from the local HF cache (#7273) 2026-07-21 02:48:19 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
_platform_compat.py Reduce and tighten code comments and docstrings repo-wide (#6095) 2026-06-08 23:09:51 -07:00
cloudflare_tunnel.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
colab.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
main.py Feat/model picker per model config v2 (#7207) 2026-07-20 22:53:22 -07:00
mcp_server.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
run.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00
startup_banner.py Replace standalone Studio wording with Unsloth (#7221) 2026-07-19 00:47:04 -07:00