Histórico de Commits

Autor SHA1 Mensagem Data
  Alex Cheema 99a70f1045 Merge commit: trigger test há 7 meses atrás
  Alex Cheema bd0febe35f Merge commit: trigger test há 7 meses atrás
  Alex Cheema 34ecbbe01c Merge commit: trigger test há 7 meses atrás
  Alex Cheema 427d0718b3 Merge commit: trigger test há 7 meses atrás
  Alex Cheema b49c4ca0e5 Merge commit: trigger test há 7 meses atrás
  Alex Cheema 41eaaec5a9 Merge commit: trigger test há 7 meses atrás
  Alex Cheema bf1aafdea7 Merge commit: trigger test há 7 meses atrás
  Alex Cheema bfa06ee9f3 Merge commit: trigger test há 7 meses atrás
  Alex Cheema c0534b67c3 Merge commit: trigger test há 7 meses atrás
  Alex Cheema 063964aab3 remove redundant sample_logits, put back opaque status for process_prompt so we have a way of preemptively starting downloads há 7 meses atrás
  Alex Cheema 804ad4705a upgrade mlx há 7 meses atrás
  Alex Cheema c9ded9ba96 optimise networking, remove bloat há 7 meses atrás
  Alex Cheema 64365d684f one two and three m4 pro clusters há 7 meses atrás
  Alex Cheema 9397464fad add commit to results há 7 meses atrás
  Nel Nibcord 08912d1b64 Only collect topology if peers changed há 7 meses atrás
  Alex Cheema 06c2e236b8 rip out stats bloat há 7 meses atrás
  Alex Cheema cb4615c95d fix SendNewToken há 7 meses atrás
  Alex Cheema f55a53ae7e one token at a time há 7 meses atrás
  Gary 25b4af70e0 Merge branch 'main' into runners há 7 meses atrás
  Alex Cheema a93092105c set max-generate-tokens to 250 há 7 meses atrás
  Alex Cheema 0c6ab35333 increase timeout of http request in bench.py up to 10 mins há 7 meses atrás
  Alex Cheema 72be5e4bd5 Merge pull request #556 from exo-explore/fixtestmodelhelpers há 7 meses atrás
  Alex Cheema b0e079b36a fix counts in testmodelhelpers há 7 meses atrás
  Alex Cheema e5d54c77a9 add llama-3.3-70b to 3 M4 Pro cluster há 7 meses atrás
  Alex Cheema 2ff4638122 Merge remote-tracking branch 'origin/main' into runners há 7 meses atrás
  Alex Cheema 342b5d8ac0 Merge pull request #555 from exo-explore/modelvariations há 7 meses atrás
  Alex Cheema a0bada3b2a add llama-3.2-1b-8bit, llama-3.2-3b-8bit, llama-3.2-3b-bf16 há 7 meses atrás
  Alex Cheema b6f2385c41 run llama-3.1-8b on 3 m4 pro cluster há 7 meses atrás
  Alex Cheema 9472ab0d2c t há 7 meses atrás
  Alex Cheema dbb7ad3c08 run with three m4 pro há 7 meses atrás