 Alex Cheema
|
647ffb94eb
increase cli generation timeout
|
11 月之前 |
|
Alex Cheema
|
dd24e7db1e
only ignore CancelledError inside stop
|
11 月之前 |
|
Alex Cheema
|
2e1233357c
ignore CancelledError when stopping the server
|
11 月之前 |
 Alex Cheema
|
dfa3fdcf08
Merge pull request #161 from exo-explore/cli
|
11 月之前 |
|
Alex Cheema
|
ae35ada19b
fix headless mode with --disable-tui
|
11 月之前 |
|
Alex Cheema
|
b95916e0b5
show prompts and outputs in tui
|
11 月之前 |
|
Alex Cheema
|
e84304317c
add a cli that can be triggered with --run-model <model> --prompt <prompt>
|
11 月之前 |
|
Alex Cheema
|
cea9b48d24
update mlx-lm to 0.17.0, use lru caches for kv_cache with RotatingKVCache to optimise memory fixes #158
|
11 月之前 |
|
Alex Cheema
|
9c645b14f1
Merge pull request #157 from exo-explore/astra
|
11 月之前 |
|
Alex Cheema
|
430d4c0cf8
astra clarify readme, it's an example app
|
11 月之前 |
|
Alex Cheema
|
e87e7260f8
astra: live camera with overlay debug info / ui
|
11 月之前 |
|
Alex Cheema
|
1a419f1f00
astra better ui with camera vlm
|
11 月之前 |
|
Alex Cheema
|
8503543894
fix streaming, change default model to llava
|
11 月之前 |
|
Alex Cheema
|
c94ffa0e2b
fix audio buffering
|
11 月之前 |
|
Alex Cheema
|
23c713c012
better readme for astra
|
11 月之前 |
|
Alex Cheema
|
2fe3a52d60
readme for astra example
|
11 月之前 |
|
Alex Cheema
|
ff71ccc63d
send api request in astra example
|
11 月之前 |
|
Alex Cheema
|
b85d1956bc
open source astra example
|
11 月之前 |
|
Alex Cheema
|
e2e98c30a5
Update README.md
|
11 月之前 |
|
Alex Cheema
|
c4b261daf1
Update README.md
|
1 年之前 |
|
Alex Cheema
|
0e2ae28d36
trigger test
|
1 年之前 |
|
Alex Cheema
|
92dbb3204d
update mlx to 0.16.3
|
1 年之前 |
|
Alex Cheema
|
c4238e7d25
Merge pull request #151 from sammcj/patch-2
|
1 年之前 |
|
Alex Cheema
|
9b8e1bcddc
trigger test
|
1 年之前 |
 Sam
|
1819df36f5
Add common RTX A series cards to device_capabilities.py
|
1 年之前 |
|
Alex Cheema
|
a930be4fd9
t
|
1 年之前 |
|
Alex Cheema
|
53ec180d40
fix test import
|
1 年之前 |
|
Alex Cheema
|
611085b38d
trigger test
|
1 年之前 |
|
Alex Cheema
|
2a214db7a4
rm tokenizer from test
|
1 年之前 |
|
Alex Cheema
|
803dffd1c4
always call convert_from_huggingface with tinygrad models. this was broken by shard layer filtering which made the check sometimes fail. fixes #144
|
1 年之前 |
