1movmedia/pyworker
2
0
Fork 0
Code Pull Requests Activity
181 Commits 69 Branches 0 Tags
bd3e0032a1c4df91d9f0e3e9b52918b52ccc6041
Commit Graph
59 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
LucasArmandVastandGitHub bd3e0032a1 Add SDK version checking (#76) 2025-12-17 21:01:52 -08:00
Lucas Armand e02f4bc943 Lowered concurrency of vLLM and TGI benchmarks 2025-12-17 11:55:33 -08:00
Lucas Armand bcb04b9a32 add missing comma 2025-12-17 11:40:40 -08:00
Lucas Armand 9daf171487 Increase queue limits for vLLM and TGI 2025-12-17 11:38:55 -08:00
LucasArmandVastandGitHub 29f836eb1a Backwards compatible vLLM payload (#75) 
* Support old vLLM payloads
 2025-12-15 19:58:02 -08:00
LucasArmandVastandGitHub 4380d98c01 Use PyWorker SDK (#67) 
* Change PyWorker to Worker SDK
* Moved /lib to vast-sdk (https://github.com/vast-ai/vast-sdk)
 2025-12-15 19:33:03 -08:00
LucasArmandVastandGitHub 70f8a8f534 Merge pull request #72 from vast-ai/hotfix-pin-pycares 
Hotfix: pin pycares
 2025-12-10 20:41:44 -05:00
Lucas Armand 7be8aa6397 pin pycares 2025-12-10 17:38:03 -08:00
LucasArmandVastandGitHub 2f543c01ad Merge pull request #68 from vast-ai/fix-vllm-concurrency 
Increase model wait time for vLLM
 2025-12-03 16:13:51 -05:00
Lucas Armand 0bcd2219ea Increase model wait time for vLLM 2025-12-03 12:38:52 -08:00
LucasArmandVastandGitHub 0339b471c5 Merge pull request #66 from vast-ai/synthesis 
PyWorker Error Handling
 2025-11-25 16:02:26 -08:00
Lucas Armand e143162438 bumpy pyworker version 2025-11-25 16:01:23 -08:00
Lucas Armand 7986e51e9e early errors 2025-11-24 15:24:06 -08:00
Lucas Armand 9c6ab78503 Move model log line 2025-11-24 15:22:23 -08:00
Lucas Armand 45e0c7d9ca Move model log rotate to top 2025-11-24 15:02:33 -08:00
LucasArmandVastandGitHub 7a792fd176 Merge pull request #64 from vast-ai/add-llama-log 
add llama log
 2025-11-21 10:24:27 -08:00
Lucas Armand e0449cb3c7 add llama log 2025-11-21 10:22:16 -08:00
Lucas Armand a4339bd3f1 hotfix: add f 2025-11-12 16:10:55 -08:00
Lucas Armand 2b26e5e20c hotfix: remove g 2025-11-12 16:01:57 -08:00
LucasArmandVastandGitHub d3727d4fd7 Merge pull request #58 from vast-ai/update-client-scripts 
Update client scripts
 2025-11-12 10:22:42 -08:00
Lucas Armand a47c9d1ed0 remove test bugs 2025-11-11 18:13:46 -08:00
Lucas Armand 0b14562a63 dont exit on pyworker fail 2025-11-11 17:57:08 -08:00
Lucas Armand de9b50abb9 use set +e 2025-11-11 17:53:36 -08:00
Lucas Armand c510801723 fix 2025-11-11 17:49:34 -08:00
Lucas Armand a12523b1d2 Added bad code to tgi server to test 2025-11-11 17:41:12 -08:00
Lucas Armand eedf81c0a3 Updated readme and .gitignore 2025-11-11 17:18:40 -08:00
Lucas Armand 3adec1826d minor changes 2025-11-11 17:11:38 -08:00
Lucas Armand b55bfa9611 Updated clients, include vastai-sdk, handle non-UTF-8 2025-11-11 17:09:28 -08:00
LucasArmandVastandGitHub 7db54f3bd7 Merge pull request #55 from vast-ai/use-mtoken 
Use mtoken
 2025-11-10 11:54:04 -08:00
LucasArmandVastandGitHub d63a060202 Merge pull request #56 from vast-ai/obfuscate-mtoken 
Obfuscate mtoken in logs
 2025-11-10 11:53:17 -08:00
Lucas Armand c6521cb6d4 add ... 2025-11-07 10:10:35 -08:00
Lucas Armand b7fe4ebb91 Obfuscate mtoken in logs 2025-11-07 10:02:39 -08:00
Lucas Armand 8ae7b74605 bump version to 0.2.0 2025-11-05 13:32:21 -08:00
Lucas Armand 106067d716 bump version to 0.1.1 2025-11-04 17:15:59 -08:00
Lucas Armand f5134d4bf5 Fix spelling mistake 2025-11-04 16:59:39 -08:00
Lucas Armand 47e5460532 added mtoken 2025-11-04 15:55:14 -08:00
LucasArmandVastandGitHub 9f5a432513 Merge pull request #51 from vast-ai/delete-reqs-hotfix 
Redis subscriber queue patch
 2025-10-28 16:07:28 -07:00
Lucas Armand e09f1fa953 patch for redis queue 2025-10-28 16:03:50 -07:00
Lucas Armand 814c3acd4c remove unused code 2025-10-28 13:43:57 -07:00
Lucas Armand 22bca74087 Prevent load time race 2025-10-27 18:25:21 -07:00
Lucas Armand 9c795e2a01 removed bad code 2025-10-27 17:03:13 -07:00
Lucas Armand 830b532781 Trying unified delete 2025-10-27 16:57:52 -07:00
LucasArmandVastandGitHub d6a6e34c6b Merge branch 'main' into new-pyworker 2025-10-27 12:43:49 -07:00
Lucas Armand 4d9bf2048c Fix 2025-10-24 15:44:38 -07:00
Lucas Armand 7788bc4a62 Added some debug logs 2025-10-24 15:41:00 -07:00
Lucas Armand 37ad3f8d46 asyncio in metrics 2025-10-23 10:18:31 -07:00
Lucas Armand 0f13506938 Send success param 2025-10-22 10:18:59 -07:00
Lucas Armand 01e752d31f use more asyncio sleep 2025-10-21 18:52:13 -07:00
Lucas Armand 5edfa968ca async sleep 2025-10-21 18:49:48 -07:00
Lucas Armand 5b5ef7227a nvm moved it here 2025-10-21 18:20:11 -07:00
Lucas Armand 16990ff8ff move start request 2025-10-21 18:18:44 -07:00
Lucas Armand 9748176366 fixed semaphore acquire bool 2025-10-21 18:12:23 -07:00
Lucas Armand b39193ae70 check for sem acquire 2025-10-21 18:02:14 -07:00
Lucas Armand 9a6ca5d412 added versioning 2025-10-21 15:42:43 -07:00
Lucas Armand e9ba1b03e4 Use delete_requests and track request_idxs 2025-10-21 11:59:35 -07:00
LucasArmandVastandGitHub c98d661513 Merge pull request #39 from vast-ai/remove-time-divide 
PyWorker fixes for cur_load and acks bug
 2025-10-13 10:06:22 -07:00
Lucas Armand f6fd1c6ac1 merge 2025-10-09 18:15:55 -07:00
Lucas Armand 055e346c8c Send metrics on request start 2025-10-09 10:13:50 -07:00
Lucas Armand 1cedb28acf Removed division by elapsed time, since autoscaler cur_load in units of workload 2025-10-08 16:54:18 -07:00