Commit Graph

98 Commits

Author SHA1 Message Date
Colter-Downing ac1e109c48 Merge pull request #47 from vast-ai/new-pyworker-vllm-prefix-cache
vLLM Prefix caching, benchmark bug fix, test load script
2025-10-27 12:30:34 -07:00
Colter Downing d6eb498ee4 catch the case where all benchmarks fail (sets error) 2025-10-27 12:01:55 -07:00
Colter Downing bcecd6df40 Suppress matplot debug logs 2025-10-25 16:18:02 -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
Rob Ballantyne 4fdc314fd9 Fix healthcheck endpoint URL 2025-10-06 22:16:09 +01:00
Colter-Downing 639d82f5b4 Merge pull request #35 from vast-ai/AUTO-664--Healthcheck-error
Fix healthcheck with separate session
2025-10-02 12:51:19 -07:00
Colter Downing 25db78e39d Fix healthcheck with separate session 2025-10-01 18:04:31 -07:00
Scott-Laytart 4e2f2311d0 Merge pull request #33 from vast-ai/comfy-blind-fix-override
undo the fix for comfy yesterday.
2025-09-03 11:50:07 -07:00
abiola-vastai 38782d89bc undo the fix for comfy yesterday. 2025-09-03 17:12:35 +00:00
Scott-Laytart 0185216ccb Merge pull request #32 from vast-ai/blindhotfix_comfy_ui_default_port
Blind hotfix to see if comfy UI default is needed. if it does work we…
2025-09-02 18:26:25 -07:00
abiola-vastai b20d9e714c Blind hotfix to see if comfy UI default is needed. if it does work we would revert back. 2025-09-03 01:20:09 +00:00
Rob Ballantyne b1eb65d75d Merge pull request #31 from vast-ai/bugfix/startup-script-20250901
Update uv venv creation command
2025-09-01 18:19:17 +01:00
Rob Ballantyne 1d09d7fe96 Update uv venv creation command 2025-09-01 16:55:20 +01:00
Colter-Downing 1b37054dec Merge pull request #28 from vast-ai/bugfix/backend-timeout-infinite
Bugfix/backend timeout infinite
2025-08-28 11:22:33 -07:00
Colter-Downing 1a1e4174b8 Merge pull request #29 from vast-ai/bugfix/comfyui-json-cost-fix
Set cost to 100
2025-08-28 11:22:21 -07:00
Rob Ballantyne b8377c4081 Set cost to 100 2025-08-28 16:13:17 +01:00
Rob Ballantyne 1e4fa87437 Prevent timeout and allow long running connections 2025-08-28 15:48:57 +01:00
Rob Ballantyne 4c5fa03c7b adds import for ClientTimeout 2025-08-27 20:54:27 +01:00
Rob Ballantyne a8fe74f771 Remove default 300s timeout 2025-08-27 18:34:45 +01:00
Rob Ballantyne b482de8394 Merge pull request #27 from vast-ai/feat/comfyui-api-s3-webhook
Adds new ComfyUI worker

Upload assets to s3 compatible storage via intermediate API wrapper
2025-08-26 14:22:05 +01:00
Rob Ballantyne 703435d10e Improve MODEL_SERVER_START_* messages 2025-08-26 12:42:04 +01:00
Rob Ballantyne 947fc5eea4 Improve benchmarking explanation 2025-08-26 12:41:30 +01:00
Rob Ballantyne 7c1a544b19 Improve error reporting when no ready workers 2025-08-26 12:41:05 +01:00
Rob Ballantyne 16b414676e Use count_workload() function for cost 2025-08-25 18:31:10 +01:00
Rob Ballantyne ba74ac8136 Use cost value 1 for all jobs 2025-08-25 17:58:22 +01:00
Rob Ballantyne 92ff412679 Use MODEL_SERVER_URL environment variable 2025-08-25 17:57:32 +01:00
Rob Ballantyne fc75a64684 Use MODEL_SERVER_URL environment variable 2025-08-25 17:56:27 +01:00
Rob Ballantyne b00bef547c Ensure uv env script is present before sourcing 2025-08-22 17:08:42 +01:00
Rob Ballantyne 3f4acb29fa Improved client exception handling 2025-08-22 15:20:15 +01:00
Rob Ballantyne 58b078f908 Fix modifier class 2025-08-20 18:06:02 +01:00
Rob Ballantyne f9fdf04884 Fix signature 2025-08-20 13:27:29 +01:00
Rob Ballantyne 636f17d27f Fix workflow modifier class 2025-08-20 09:57:07 +01:00
Rob Ballantyne 08c88f7527 Improve testability 2025-08-20 09:34:09 +01:00
Rob Ballantyne 8797b504af Initial ComfyUI implementation with updated wrapper 2025-08-19 17:59:20 +01:00
Nader Arbabian cd946b0a9f update report_addr to use new webserver endpoint with AS fallback 2025-08-12 13:31:19 -07:00
Nader Arbabian c595b42410 for benchmarking, use concurrent requests (#26) 2025-08-11 12:39:28 -07:00
Nader Arbabian 0bf3247a34 fix completions and interactive client 2025-08-11 12:37:53 -07:00
Nader Arbabian 52ac4c0c1a fix endpoint_util not using the correct instance's endpoint 2025-08-11 12:05:58 -07:00
Nader Arbabian 8804e17201 download vast.ai's root certificate in order to make pyworker requests (#25) 2025-08-08 17:04:16 -07:00