Commit Graph

Select branches

Hide Pull Requests

AUTO-664--Healthcheck-error

AUTO-695

AUTO-702--improved-test-load

AUTO-703-comfyui-json-error

AUTO-848--endpoint-id-routing

AUTO-874--fix-openai-worker-client

AUTO-912

AUTO-comfyui-updates

AUTO-tgi-client-edits

HOTFIX-aiohttp-version

add-hacky-deployments-script

add-llama-log

add-ntlk-requirement

allow-prerelease-pip

batched-wait-time

blindhotfix_comfy_ui_default_port

bugfix/backend-timeout-infinite

bugfix/comfyui-json-cost-fix

bugfix/startup-script-20250901

comfy-blind-fix-override

comfy-queue

comfy-request-idx

comfyui-benchmark-model-type

delete-reqs-hotfix

deployments-direct-executable

experiment/null-worker

feat/comfyui-api-s3-webhook

fifo-queue

fix-bad-model-rotate

fix-signature

fix-vllm-concurrency

fix/better-benchmarks

fix/comfyui-restore-benchmark-json-loading

fix/fetch-vast-certificate-for-pyworker-client

fix/fix-pyright-and-revert-cancelled-http-request-handling

fix/more-robust-tracking-of-pending-request

fix/pyworker-num-requests-working

fix/reduce-dependencies

force-update-flag

hotfix-pin-pycares

hotfix-vllm-parsing

kill-pub-sub

main

model-log-rotation

new-pyworker

new-pyworker-vllm-cold-start-timing

new-pyworker-vllm-prefix-cache

no-input

obfuscate-mtoken

pyworker-failure-reporting

pyworker-force-update-and-retry

pyworker-queue

pyworker-sdk

read-model-log

remove-sleeps-and-delays

script-testing-new-pyworker

sdk-versioning

send-metrics-on-req-start

serverside-sdk

session

shallow-git-clone

synthesis

synthesis_fix

test-package

unsecure_report_addr

update-client-scripts

update-requirements

use-mtoken

use-vastai

Mono Color

• 6a57ff8e0a try reverting env var Lucas Armand 2025-12-12 12:16:33 -08:00
• 375633cb18 Fix Lucas Armand 2025-12-12 12:12:57 -08:00
• ccd29ed8b6 remove input wrapping for vllm Lucas Armand 2025-12-12 11:48:54 -08:00
• 2b30c69933 updated cost Lucas Armand 2025-12-12 10:43:05 -08:00
• 4d99c12820 Added clients, updated READMEs Lucas Armand 2025-12-12 10:41:21 -08:00
• 6060f8ce0c updated start_server.sh Lucas Armand 2025-12-12 10:04:33 -08:00
• 2ce741a8b7 Merge pull request #74 from vast-ai/AUTO-912 Abiola Akinnubi 2025-12-11 17:05:13 -08:00
• 067fa936fb remove legacy pyworker Lucas Armand 2025-12-11 16:55:48 -08:00
• 4ecc07032f Mark pyworkers as "Error" if startup script fails. to avoid silent fail that waits for autoscaler. AUTO-912 Abiola Akinnubi 2025-12-11 12:51:56 -08:00
• df61e6e946 correct version pin for aiohttp (#73) edgaratvast 2025-12-10 19:34:52 -08:00
• fdd50a2aaa correct version pin for aiohttp HOTFIX-aiohttp-version Edgar Lin 2025-12-10 19:14:34 -08:00
• 70f8a8f534 Merge pull request #72 from vast-ai/hotfix-pin-pycares LucasArmandVast 2025-12-10 20:41:44 -05:00
• 7be8aa6397 pin pycares hotfix-pin-pycares Lucas Armand 2025-12-10 17:38:03 -08:00
• 405a8f1c0d returned to worker-sdk no-input Lucas Armand 2025-12-10 16:37:09 -08:00
• 12f4f23d39 remove parse request Lucas Armand 2025-12-10 15:16:23 -08:00
• e2a771bb5a update ace and wan workers Lucas Armand 2025-12-10 15:09:27 -08:00
• 0cd64adfc4 remove input Lucas Armand 2025-12-10 14:47:47 -08:00
• 6f795b8fb8 remove input from workers Lucas Armand 2025-12-10 14:46:10 -08:00
• 68d8ce4bfd refactor: use endpoint_id instead of endpoint name for routing AUTO-848--endpoint-id-routing Colter Downing 2025-12-06 14:46:41 -08:00
• 138fc3ac47 Merge pull request #71 from vast-ai/AUTO-comfyui-updates Colter-Downing 2025-12-04 10:55:12 -08:00
• 222ac2a0dd default endpoint name AUTO-comfyui-updates Colter Downing 2025-12-04 10:54:55 -08:00
• 40aed9b5f8 adding s3 as an option Colter Downing 2025-12-04 10:52:57 -08:00
• d4d36bf86e done with comfy updates Colter Downing 2025-12-03 20:45:55 -08:00
• e839cfc6e8 include view in API wrapper Colter Downing 2025-12-03 20:22:45 -08:00
• f04138e13b update to be able to get images Colter Downing 2025-12-03 20:16:25 -08:00
• de3aa87c8f Merge pull request #70 from vast-ai/AUTO-tgi-client-edits Colter-Downing 2025-12-03 18:40:01 -08:00
• 6b5b1341a7 update tgi client AUTO-tgi-client-edits Colter Downing 2025-12-03 18:38:42 -08:00
• 8be92c03de Merge pull request #69 from vast-ai/AUTO-874--fix-openai-worker-client Colter-Downing 2025-12-03 16:59:56 -08:00
• adedb8ba90 defaults to ENDPOINT_NAME and DEFAULT_MODEL but uses the flag first if present AUTO-874--fix-openai-worker-client Colter Downing 2025-12-03 16:57:28 -08:00
• 2f543c01ad Merge pull request #68 from vast-ai/fix-vllm-concurrency LucasArmandVast 2025-12-03 16:13:51 -05:00
• 0bcd2219ea Increase model wait time for vLLM fix-vllm-concurrency Lucas Armand 2025-12-03 12:38:52 -08:00
• 4bcc508473 reduce vllm benchmark runs to 2 Lucas Armand 2025-11-25 16:54:17 -08:00
• 74d7330800 add wan and ace workers Lucas Armand 2025-11-25 15:45:25 -08:00
• 2ce0450809 Add worker.pys Lucas Armand 2025-11-25 13:33:12 -08:00
• 0339b471c5 Merge pull request #66 from vast-ai/synthesis LucasArmandVast 2025-11-25 16:02:26 -08:00
• e143162438 bumpy pyworker version synthesis Lucas Armand 2025-11-25 16:01:23 -08:00
• 62fbfb061d more logs synthesis_fix Colter Downing 2025-11-24 18:40:45 -08:00
• c772e1651b debug logs Colter Downing 2025-11-24 18:21:35 -08:00
• ecc6a3ce0d catch all exceptions, add logs Colter Downing 2025-11-24 18:06:17 -08:00
• 7986e51e9e early errors Lucas Armand 2025-11-24 15:24:06 -08:00
• 9c6ab78503 Move model log line fix-bad-model-rotate Lucas Armand 2025-11-24 15:22:23 -08:00
• 45e0c7d9ca Move model log rotate to top Lucas Armand 2025-11-24 15:02:33 -08:00
• 7a792fd176 Merge pull request #64 from vast-ai/add-llama-log LucasArmandVast 2025-11-21 10:24:27 -08:00
• e0449cb3c7 add llama log add-llama-log Lucas Armand 2025-11-21 10:22:16 -08:00
• 63550d5af3 Actual fix -- MOVED TO TEMPLATE read-model-log Lucas Armand 2025-11-17 10:57:55 -08:00
• 7ec0e11938 add await Lucas Armand 2025-11-17 10:46:09 -08:00
• 191fbbfe18 try seek Lucas Armand 2025-11-17 10:44:13 -08:00
• 9a4a39c71b Read model log Lucas Armand 2025-11-17 10:32:38 -08:00
• 74efc2cb42 bump up version minor number AUTO-695 Abiola Akinnubi 2025-11-14 18:07:17 -08:00
• db3096bbaf feat AUTO-695: add loaded_at attribute to AutoScalerData and Metrics classes Abiola Akinnubi 2025-11-14 15:50:08 -08:00
• a4339bd3f1 hotfix: add f Lucas Armand 2025-11-12 16:10:55 -08:00
• 2b26e5e20c hotfix: remove g Lucas Armand 2025-11-12 16:01:57 -08:00
• 249ca2eb99 refactor, handle zombie tasks fifo-queue Lucas Armand 2025-11-12 15:23:42 -08:00
• d8bb1fcc68 add fifo queue Lucas Armand 2025-11-11 18:53:17 -08:00
• d3727d4fd7 Merge pull request #58 from vast-ai/update-client-scripts LucasArmandVast 2025-11-12 10:22:42 -08:00
• a47c9d1ed0 remove test bugs pyworker-failure-reporting Lucas Armand 2025-11-11 18:13:46 -08:00
• 0b14562a63 dont exit on pyworker fail Lucas Armand 2025-11-11 17:57:08 -08:00
• de9b50abb9 use set +e Lucas Armand 2025-11-11 17:53:36 -08:00
• c510801723 fix Lucas Armand 2025-11-11 17:49:34 -08:00
• a12523b1d2 Added bad code to tgi server to test Lucas Armand 2025-11-11 17:41:12 -08:00
• eedf81c0a3 Updated readme and .gitignore update-client-scripts Lucas Armand 2025-11-11 17:18:40 -08:00
• 3adec1826d minor changes Lucas Armand 2025-11-11 17:11:38 -08:00
• b55bfa9611 Updated clients, include vastai-sdk, handle non-UTF-8 Lucas Armand 2025-11-11 17:09:28 -08:00
• 353462ecb8 try allow parallel requests comfy-queue Lucas Armand 2025-11-11 11:27:05 -08:00
• 7db54f3bd7 Merge pull request #55 from vast-ai/use-mtoken LucasArmandVast 2025-11-10 11:54:04 -08:00
• d63a060202 Merge pull request #56 from vast-ai/obfuscate-mtoken use-mtoken LucasArmandVast 2025-11-10 11:53:17 -08:00
• c6521cb6d4 add ... obfuscate-mtoken Lucas Armand 2025-11-07 10:10:35 -08:00
• b7fe4ebb91 Obfuscate mtoken in logs Lucas Armand 2025-11-07 10:02:39 -08:00
• 8ae7b74605 bump version to 0.2.0 Lucas Armand 2025-11-05 13:32:21 -08:00
• 106067d716 bump version to 0.1.1 Lucas Armand 2025-11-04 17:15:59 -08:00
• f5134d4bf5 Fix spelling mistake Lucas Armand 2025-11-04 16:59:39 -08:00
• 47e5460532 added mtoken Lucas Armand 2025-11-04 15:55:14 -08:00
• c9d701e8d3 increase wait time for llm backends batched-wait-time Lucas Armand 2025-11-03 16:21:56 -08:00
• ec2ac0a21a Merge pull request #52 from vast-ai/remove-sleeps-and-delays Colter-Downing 2025-10-30 11:53:39 -07:00
• 2cde573c56 Merge pull request #48 from vast-ai/comfy-request-idx Abiola Akinnubi 2025-10-30 11:27:35 -07:00
• b2e4a5db0c Merge pull request #49 from vast-ai/unsecure_report_addr Abiola Akinnubi 2025-10-30 10:39:46 -07:00
• b03645d145 Added model type environment variable so we can actually attempt to benchmark with the right payload. comfyui-benchmark-model-type Abiola Akinnubi 2025-10-28 19:22:47 +00:00
• 7437028cb2 Added caller for REPORT_ADDR to backend.py unsecure_report_addr Abiola Akinnubi 2025-10-27 19:53:31 +00:00
• 02c8307af7 remove redis pubsub from pyworker (#53) edgaratvast 2025-10-29 17:07:56 -07:00
• 7d43bc8d68 remove redis pubsub from pyworker kill-pub-sub Edgar Lin 2025-10-29 11:46:31 -07:00
• 7c0f316eeb leave the env vars alone! remove-sleeps-and-delays Colter Downing 2025-10-29 11:36:46 -07:00
• b4025a744f remove env var writing Colter Downing 2025-10-28 16:11:35 -07:00
• d190308329 removed 5 sec sleep and warmup request on load Colter Downing 2025-10-28 15:28:30 -07:00
• fd9d56e576 remove env var writing new-pyworker-vllm-cold-start-timing Colter Downing 2025-10-28 16:11:35 -07:00
• 9f5a432513 Merge pull request #51 from vast-ai/delete-reqs-hotfix LucasArmandVast 2025-10-28 16:07:28 -07:00
• e09f1fa953 patch for redis queue delete-reqs-hotfix Lucas Armand 2025-10-28 16:03:50 -07:00
• ba6f1c2e4b Fix signature (#50) edgaratvast 2025-10-28 16:01:32 -07:00
• 8d9ffb3a6c removed 5 sec sleep and warmup request on load Colter Downing 2025-10-28 15:28:30 -07:00
• 50f13d6288 enforce alphabetical json dumping of message for signature verification fix-signature Edgar Lin 2025-10-28 15:21:14 -07:00
• a6921de6a2 Revert "change order of fields in auth_data to match autoscaler for signature verification" so that it's alphabetical again Edgar Lin 2025-10-28 15:18:41 -07:00
• dcb7d036ed also ignore __request_id Edgar Lin 2025-10-28 15:03:18 -07:00
• b8223879c9 change order of fields in auth_data to match autoscaler for signature verification Edgar Lin 2025-10-28 14:51:03 -07:00
• 944f83fc03 Removed extra spaces from operator assignment comfy-request-idx Abiola Akinnubi 2025-10-28 21:03:52 +00:00
• 298590fb88 Merge pull request #45 from vast-ai/new-pyworker edgaratvast 2025-10-28 14:02:53 -07:00
• 814c3acd4c remove unused code new-pyworker Lucas Armand 2025-10-28 13:43:57 -07:00
• 22bca74087 Prevent load time race Lucas Armand 2025-10-27 18:25:21 -07:00
• 0471f6b219 trying queue pyworker-queue Lucas Armand 2025-10-27 17:34:37 -07:00
• 9c795e2a01 removed bad code Lucas Armand 2025-10-27 17:03:13 -07:00
• 830b532781 Trying unified delete Lucas Armand 2025-10-27 16:57:52 -07:00
• d6a6e34c6b Merge branch 'main' into new-pyworker LucasArmandVast 2025-10-27 12:43:49 -07:00