 Alex Cheema
|
f5764f3756
prefill in batches to prevent oom on very long prompts
|
hai 8 meses |
|
Alex Cheema
|
d917778e2b
update mlx to 0.17.1 (not sure where 0.17.0 went on PyPi disappeared)g
|
hai 8 meses |
|
Alex Cheema
|
09a8468395
upgrade mlx to 0.17.0
|
hai 8 meses |
|
Alex Cheema
|
2e27076665
simplify formatting with yapf
|
hai 8 meses |
|
Alex Cheema
|
cea9b48d24
update mlx-lm to 0.17.0, use lru caches for kv_cache with RotatingKVCache to optimise memory fixes #158
|
hai 9 meses |
|
Alex Cheema
|
92dbb3204d
update mlx to 0.16.3
|
hai 9 meses |
|
Alex Cheema
|
440fd35ea7
upgrade aiohttp
|
hai 9 meses |
|
Alex Cheema
|
71591d2ebc
display all interfaces web chat and chatgpt api are available on fixes #134
|
hai 9 meses |
|
Alex Cheema
|
35b7042e70
upgrade mlx to 0.16.1
|
hai 9 meses |
|
Alex Cheema
|
545a486ed3
separate hf_helpers, make extra dir with download_hf script, unify downloading so tinygrad uses the same method as mlx and interoperable model formats
|
hai 9 meses |
|
Alex Cheema
|
d6a7e46324
async model downloading with download progress. fixes #102. related: #16 #104
|
hai 9 meses |
|
Alex Cheema
|
78db451d7e
add pillow to main dependencies
|
hai 9 meses |
|
Alex Cheema
|
824f05263f
Merge branch 'main' into HEAD
|
hai 9 meses |
|
Alex Cheema
|
142682645f
bump up tinygrad version
|
hai 9 meses |
 Varshith
|
acc94b50c7
chatgpt api integration
|
hai 9 meses |
|
Alex Cheema
|
b44b917151
add pillow as testing dependency
|
hai 9 meses |
|
Alex Cheema
|
ce761038ac
formatting / linting
|
hai 9 meses |
|
Alex Cheema
|
bbfd5adc20
add support for llama3.1 (8b, 70b, 405b). bump mlx up to 0.16.0 and mlx-lm up to 0.16.1. fixes #66
|
hai 9 meses |
|
Alex Cheema
|
4e46232364
add simple prometheus metrics collection, with a prometheus / grafana instance for live dashboard. related: #22
|
hai 9 meses |
|
Alex Cheema
|
4b592f9d45
exo topology visualisation that shows the topology of the network, device capabilities and the currently active node using opaque statuses. fixes #36. ready for #33
|
hai 10 meses |
|
Alex Cheema
|
46d618abed
tiny fixes
|
hai 10 meses |
|
Alex Cheema
|
071b1caa0b
drop exo to 0.0.1 (still experimental)
|
hai 10 meses |
|
Alex Cheema
|
8762effaf4
chatgpt api repsonse streaming solves #20
|
hai 10 meses |
|
Alex Cheema
|
998d484384
match psutil platform detection might catch some edge cases
|
hai 10 meses |
 Alex
|
bfaeccc7d5
added setup py
|
hai 10 meses |
