Commit Graph

177 Commits

Author SHA1 Message Date
Cyberes f9b9051bad update weighted_average_column_for_model to account for when there was an error reported, insert null for response tokens when error, correctly parse x-forwarded-for, correctly convert model reported by hf-textgen 2023-08-29 15:46:56 -06:00
Cyberes da77a24eaa damn 2023-08-29 14:58:08 -06:00
Cyberes 2d9ec15302 I swear I know what I'm doing 2023-08-29 14:57:49 -06:00
Cyberes 06b52c7648 forgot to remove a snippet 2023-08-29 14:53:03 -06:00
Cyberes 23f3fcf579 log errors to database 2023-08-29 14:48:33 -06:00
Cyberes b44dfa2471 update info page 2023-08-29 14:00:35 -06:00
Cyberes ba0bc87434 add HF text-generation-inference backend 2023-08-29 13:46:41 -06:00
Cyberes 6c0e60135d exclude tokens with priority 0 from simultaneous requests ratelimit 2023-08-28 00:03:25 -06:00
Cyberes c16d70a24d limit amount of simultaneous requests an IP can make 2023-08-27 23:48:10 -06:00
Cyberes 1a4cb5f786 reorganize stats page again 2023-08-27 22:24:44 -06:00
Cyberes f43336c92c adjust estimated wait time calculations 2023-08-27 22:17:21 -06:00
Cyberes 441a870e85 calculate weighted average for stat tracking 2023-08-27 19:58:04 -06:00
Cyberes 6a09ffc8a4 log model used in request so we can pull the correct averages when we change models 2023-08-26 00:30:59 -06:00
Cyberes d64152587c reorganize nvidia stats 2023-08-25 15:02:40 -06:00
Cyberes 0e6aadf5e1 fix missing empty strings logged when errors 2023-08-25 13:44:41 -06:00
Cyberes 2543db87e8 fix database error 2023-08-25 12:25:30 -06:00
Cyberes 839bb115c6 reorganize stats, add 24 hr proompters, adjust logging when error 2023-08-25 12:20:16 -06:00
Cyberes 26a0a13aa7 actually we want this 2023-08-24 23:57:46 -06:00
Cyberes 0b4da89de2 fix exception 2023-08-24 23:57:25 -06:00
Cyberes 25e3255c9b fix issue with tokenizer 2023-08-24 23:13:07 -06:00
Cyberes 77fe1e237e also handle when no response 2023-08-24 22:53:54 -06:00
Cyberes e5aca7b09d adjust netdata json, don't log error messages during generationg 2023-08-24 22:53:06 -06:00
Cyberes 06173f900e remove debug print 2023-08-24 22:02:15 -06:00
Cyberes 0230ddda17 dynamically fetch GPUs for netdata 2023-08-24 21:56:15 -06:00
Cyberes 16b986c206 track nvidia power states through netdata 2023-08-24 21:36:00 -06:00
Cyberes 01b8442b95 update current model when we generate_stats() 2023-08-24 21:10:00 -06:00
Cyberes ec3fe2c2ac show total output tokens on stats 2023-08-24 20:43:11 -06:00
Cyberes 9b7bf490a1 sort keys of stats dict 2023-08-24 18:59:52 -06:00
Cyberes c397649097 restyle homepage, add config item to add content to the home page 2023-08-24 17:55:55 -06:00
Cyberes 763dd832cc update home, update readme, calculate estimated wait based on database stats 2023-08-24 16:47:14 -06:00
Cyberes 21174750ea update readme 2023-08-24 12:19:59 -06:00
Cyberes afc138c743 update readme 2023-08-24 00:09:57 -06:00
Cyberes f7743ade89 add dynamic analitics tracking to home page 2023-08-23 23:27:33 -06:00
Cyberes c2b0fa1cf5 remove debug code 2023-08-23 23:14:50 -06:00
Cyberes f3fe514c11 add home template 2023-08-23 23:11:12 -06:00
Cyberes dca2dc570f adjust db gen time 2023-08-23 22:28:03 -06:00
Cyberes cdda2c840c dont test code, don't care 2023-08-23 22:24:32 -06:00
Cyberes 1eb8e885d0 am dumb 2023-08-23 22:22:38 -06:00
Cyberes e52acb03a4 log gen time to DB, also keep generation_elapsed under 3 min 2023-08-23 22:20:39 -06:00
Cyberes 3317bd5f1a allow hiding of more variables 2023-08-23 22:08:10 -06:00
Cyberes 11a0b6541f fix some stuff related to gunicorn workers 2023-08-23 22:01:06 -06:00
Cyberes 02c07bbd53 pycarm deeleted import 2023-08-23 21:34:27 -06:00
Cyberes de19af900f add estimated wait time and other time tracking stats 2023-08-23 21:33:52 -06:00
Cyberes 0aa52863bc forgot to start workers 2023-08-23 20:33:49 -06:00
Cyberes 6f8b70df54 add a queue system 2023-08-23 20:12:38 -06:00
Cyberes a79d67adbb do caching ourself on /model 2023-08-23 16:40:20 -06:00
Cyberes 64e1b1654f more cloudflare finicky stuff 2023-08-23 16:32:13 -06:00
Cyberes f76d7bbc5d more caching stuff 2023-08-23 16:23:24 -06:00
Cyberes 7eb930fafd crap 2023-08-23 16:12:25 -06:00
Cyberes 9fc674878d allow disabling ssl verification 2023-08-23 16:11:32 -06:00
Cyberes a6b0bb0183 actually we want 500 2023-08-23 16:09:36 -06:00
Cyberes fd5796ed07 oops 2023-08-23 16:08:52 -06:00
Cyberes 508089ce11 model info timeout and additional info 2023-08-23 16:07:43 -06:00
Cyberes 1f5e2da637 print fetch model error message 2023-08-23 16:02:57 -06:00
Cyberes 806073ee4c update config 2023-08-23 15:23:06 -06:00
Cyberes ba063f7f1b caching 2023-08-23 12:40:13 -06:00
Cyberes 33190e3cfe fix stats for real 2023-08-23 01:14:19 -06:00
Cyberes 3bb27d6900 track IPs for last min proompters 2023-08-22 23:37:39 -06:00
Cyberes 61b9e313d2 cache again 2023-08-22 23:14:56 -06:00
Cyberes 36b793e8a2 fix proompters_1_min again 2023-08-22 23:01:09 -06:00
Cyberes b051f8dd6b remove caching on stats route 2023-08-22 22:42:40 -06:00
Cyberes 9f14b166dd fix proompters_1_min, other minor changes 2023-08-22 22:32:29 -06:00
Cyberes 3d6ba923bf stats: track proompters over last minute rather than average 2023-08-22 21:55:03 -06:00
Cyberes 06ae8adf0d add backend name to error messages 2023-08-22 21:14:12 -06:00
Cyberes a525093c75 rename, more stats 2023-08-22 20:42:38 -06:00
Cyberes a9b7a7a2c7 display error messages in sillytavern 2023-08-22 20:28:41 -06:00
Cyberes 0d32db2dbd prototype hf-textgen and adjust logging 2023-08-22 19:58:31 -06:00
Cyberes a59dcea2da more proxy stats 2023-08-22 16:50:49 -06:00
Cyberes d8d5514aea add mode to stats 2023-08-22 16:41:55 -06:00
Cyberes ad9a91f1b5 concurrent gens setting, online status 2023-08-22 00:26:46 -06:00
Cyberes d250ba6484 fix redis 2023-08-22 00:01:32 -06:00
Cyberes 7d23f95d26 use redis caching 2023-08-21 23:59:50 -06:00
Cyberes 90f1381f4f fix again 2023-08-21 23:50:41 -06:00
Cyberes 9977182047 fix 2023-08-21 23:49:55 -06:00
Cyberes f767e4b076 stats: prompters 1 min 2023-08-21 23:48:06 -06:00
Cyberes e04d6a8a13 minor adjustments 2023-08-21 22:49:44 -06:00
Cyberes 8cbf643fd3 MVP 2023-08-21 21:28:52 -06:00