Commit History

Author SHA1 Message Date
  Michael Yang 094df37563 remove unused struct 1 year ago
  Bruce MacDonald bd93a94abd fix MB VRAM log output (#824) 1 year ago
  Michael Yang f55bdb6f10 Merge pull request #799 from deichbewohner/jsonmarshaling 1 year ago
  Michael Yang 2870a9bfc8 Merge pull request #812 from jmorganca/mxyng/fix-format-string 1 year ago
  Arne Müller 8fa3f366ad Removed newline trimming and used buffer directly in POST request. 1 year ago
  Michael Yang fddb303f23 fix: format string wrong type 1 year ago
  Michael Yang cb4a80b693 fix: regression unsupported metal types 1 year ago
  Arne Müller ee94693b1a handling unescaped json marshaling 1 year ago
  Michael Yang 11d82d7b9b update checkvram 1 year ago
  Michael Yang 92189a5855 fix memory check 1 year ago
  Michael Yang d790bf9916 Merge pull request #783 from jmorganca/mxyng/fix-gpu-offloading 1 year ago
  Michael Yang 35afac099a do not use gpu binary when num_gpu == 0 1 year ago
  Michael Yang 811c3d1900 no gpu if vram < 2GB 1 year ago
  Bruce MacDonald 6fe178134d improve api error handling (#781) 1 year ago
  Bruce MacDonald 56497663c8 relay model runner error message to client (#720) 1 year ago
  Michael Yang b599946b74 add format bytes 1 year ago
  Bruce MacDonald 77295f716e prevent waiting on exited command (#752) 1 year ago
  Bruce MacDonald f2ba1311aa improve vram safety with 5% vram memory buffer (#724) 1 year ago
  Bruce MacDonald 5d22319a2c rename server subprocess (#700) 1 year ago
  Bruce MacDonald 9e2de1bd2c increase streaming buffer size (#692) 1 year ago
  Michael Yang c02c0cd483 starcoder 1 year ago
  Bruce MacDonald b1f7123301 clean up num_gpu calculation code (#673) 1 year ago
  Bruce MacDonald 1fbf3585d6 Relay default values to llama runner (#672) 1 year ago
  Bruce MacDonald 9771b1ec51 windows runner fixes (#637) 1 year ago
  Michael Yang f40b3de758 use int64 consistently 1 year ago
  Bruce MacDonald 86279f4ae3 unbound max num gpu layers (#591) 1 year ago
  Bruce MacDonald 4cba75efc5 remove tmp directories created by previous servers (#559) 1 year ago
  Bruce MacDonald 1255bc9b45 only package 11.8 runner 1 year ago
  Bruce MacDonald 4e8be787c7 pack in cuda libs 1 year ago
  Bruce MacDonald 66003e1d05 subprocess improvements (#524) 1 year ago