Commit History

Author SHA1 Message Date
  Alex Cheema cea9b48d24 update mlx-lm to 0.17.0, use lru caches for kv_cache with RotatingKVCache to optimise memory fixes #158 10 months ago
  Alex Cheema 92dbb3204d update mlx to 0.16.3 10 months ago
  Alex Cheema 440fd35ea7 upgrade aiohttp 10 months ago
  Alex Cheema 71591d2ebc display all interfaces web chat and chatgpt api are available on fixes #134 10 months ago
  Alex Cheema 35b7042e70 upgrade mlx to 0.16.1 10 months ago
  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 10 months ago
  Alex Cheema d6a7e46324 async model downloading with download progress. fixes #102. related: #16 #104 11 months ago
  Alex Cheema 78db451d7e add pillow to main dependencies 11 months ago
  Alex Cheema 824f05263f Merge branch 'main' into HEAD 11 months ago
  Alex Cheema 142682645f bump up tinygrad version 11 months ago
  Varshith acc94b50c7 chatgpt api integration 11 months ago
  Alex Cheema b44b917151 add pillow as testing dependency 11 months ago
  Alex Cheema ce761038ac formatting / linting 11 months ago
  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 11 months ago
  Alex Cheema 4e46232364 add simple prometheus metrics collection, with a prometheus / grafana instance for live dashboard. related: #22 11 months ago
  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 11 months ago
  Alex Cheema 46d618abed tiny fixes 11 months ago
  Alex Cheema 071b1caa0b drop exo to 0.0.1 (still experimental) 11 months ago
  Alex Cheema 8762effaf4 chatgpt api repsonse streaming solves #20 11 months ago
  Alex Cheema 998d484384 match psutil platform detection might catch some edge cases 11 months ago
  Alex bfaeccc7d5 added setup py 11 months ago