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

• 7df01c41b4 Update log action configuration to specify model loading message main Mikhail Yevchenko 2026-06-09 12:08:10 +03:00
• 885064fba6 Update docker-in-docker feature version to 3.0.1 in devcontainer configuration Mikhail Yevchenko 2026-05-25 08:13:15 +00:00
• e8e04fe8bc Remove commented out info log actions from log configuration Mikhail Yevchenko 2026-05-21 19:55:13 +00:00
• 6cb3acdd64 Add logging import and set logger level to WARNING Mikhail Yevchenko 2026-05-21 19:50:21 +00:00
• 586ccbff1b Update log action configuration to specify detailed error and info messages Mikhail Yevchenko 2026-05-21 19:47:16 +00:00
• bcc6b62277 Update log action configuration to enable error and info logging Mikhail Yevchenko 2026-05-21 19:40:47 +00:00
• 3285d9118f Enhance completions benchmark generator to extract words from a fallback Perl copyright file Mikhail Yevchenko 2026-05-21 19:33:41 +00:00
• f77d943d79 Refactor log message handling and improve word extraction in completions benchmark Mikhail Yevchenko 2026-05-21 19:25:09 +00:00
• 976622a594 Remove nltk dep Mikhail Yevchenko 2026-05-21 19:11:53 +00:00
• 0b47ef80fb Remove version specifications for vastai-sdk and nltk in requirements.txt Mikhail Yevchenko 2026-05-21 19:10:13 +00:00
• 3898a8a651 Update model server URL to remove port specification Mikhail Yevchenko 2026-05-21 18:50:41 +00:00
• 170571714f Add log message for model load event in Ollama configuration Mikhail Yevchenko 2026-05-21 15:27:28 +00:00
• 81347ab8a0 Remove placeholder log messages for model load, error, and info Mikhail Yevchenko 2026-05-21 15:11:30 +00:00
• 6bb0097829 Refactor model configuration and update log messages for Ollama Mikhail Yevchenko 2026-05-21 15:11:25 +00:00
• 1cea6fbd2d Update model server URL and port configuration Mikhail Yevchenko 2026-05-20 13:34:45 +00:00
• 40db98915f Add devcontainer configuration for Vast.ai serverless Ollama template Mikhail Yevchenko 2026-05-18 20:38:26 +00:00
• 94926b74b6 Add log message for server listening status Mikhail Yevchenko 2026-05-18 19:42:40 +00:00
• d0347b0755 Update log file path and enhance load log messages Mikhail Yevchenko 2026-05-18 18:41:14 +00:00
• a81d3febe7 Collapse null pyworker client to a single mode parameterized by --count experiment/null-worker Rob Ballantyne 2026-05-12 12:18:33 +01:00
• 913e3a8782 Simplify null pyworker code and docs Rob Ballantyne 2026-05-12 11:50:03 +01:00
• 47ad0ebe0a Add --instance flag to null pyworker client Rob Ballantyne 2026-05-12 11:40:51 +01:00
• 34fd21e76a Revert default session cost to 100; document the over-provision as a workaround Rob Ballantyne 2026-05-12 11:34:52 +01:00
• 1d2caaf554 Default null pyworker session cost to 2x max_perf Rob Ballantyne 2026-05-12 11:31:26 +01:00
• 01eff874d8 Correct queue-time guidance for null pyworker endpoints Rob Ballantyne 2026-05-12 11:14:20 +01:00
• d51f04a176 Await endpoint.session() in null pyworker client Rob Ballantyne 2026-05-12 11:07:32 +01:00
• ef248ef695 Document endpoint scaling parameters for null pyworker Rob Ballantyne 2026-05-12 11:06:04 +01:00
• 6a562a1376 Rewrite null pyworker on the framework session model Rob Ballantyne 2026-05-12 10:51:24 +01:00
• 6c2f194b28 Add perf heartbeat to keep null pyworker reporting peak throughput Rob Ballantyne 2026-05-12 10:35:18 +01:00
• 2aada7b210 Add --plateau to null pyworker demo (default 5min) Rob Ballantyne 2026-05-11 18:26:31 +01:00
• 8df562e243 Standardize null pyworker load/perf on 150 Rob Ballantyne 2026-05-11 18:17:57 +01:00
• 4eef5e22af Pin null pyworker max_throughput to exactly 100 Rob Ballantyne 2026-05-11 18:13:16 +01:00
• 9d969e376e Standardize null pyworker load/perf on 100 Rob Ballantyne 2026-05-11 18:09:16 +01:00
• ef3f34a515 Restructure null pyworker --demo as a clean trapezoid Rob Ballantyne 2026-05-11 18:00:46 +01:00
• 147bf2597a Set null pyworker client cost to 1 Rob Ballantyne 2026-05-11 17:47:19 +01:00
• dc423e2999 Pin null pyworker benchmark to ~1.0 throughput Rob Ballantyne 2026-05-11 17:22:45 +01:00
• 463f3de8ea Add staggered --demo mode to null pyworker client Rob Ballantyne 2026-05-11 17:08:44 +01:00
• ed0db198c3 Reject queued /reserve immediately on busy null workers Rob Ballantyne 2026-05-11 17:05:02 +01:00
• 3668d948be Simplify null pyworker README intro to serverless terminology Rob Ballantyne 2026-05-11 17:02:41 +01:00
• 254ccdf181 Add /release control endpoint to null pyworker Rob Ballantyne 2026-05-11 16:59:46 +01:00
• 89761b378a Wire null pyworker healthcheck to a stub (and optional user URL) Rob Ballantyne 2026-05-11 16:53:26 +01:00
• 18974873e5 Add null pyworker for queue-driven autoscaling Rob Ballantyne 2026-05-11 16:48:52 +01:00
• b52c654f09 comfyui-json: key readiness off api-wrapper's BACKENDS_READY token fix/comfyui-restore-benchmark-json-loading Rob Ballantyne 2026-05-08 09:46:45 +01:00
• a5bcc3de5e comfyui-json: address PR #85 review Rob Ballantyne 2026-05-07 18:25:21 +01:00
• cecf0236fa comfyui-json: watch api-wrapper.log for readiness Rob Ballantyne 2026-05-07 12:46:17 +01:00
• 09917a9c88 Revert "Wait briefly for the well-known benchmark symlink" Rob Ballantyne 2026-05-07 12:03:19 +01:00
• 9d7371ddba Wait briefly for the well-known benchmark symlink Rob Ballantyne 2026-05-07 11:59:30 +01:00
• 381a39f201 Add well-known fallback path for benchmark.json Rob Ballantyne 2026-05-07 11:54:20 +01:00
• a634ba07a6 Support BENCHMARK_JSON_PATH for provisioning-supplied benchmarks Rob Ballantyne 2026-05-07 11:24:14 +01:00
• 2dd4f7fc38 Restore benchmark.json loading in comfyui-json worker Rob Ballantyne 2026-05-07 11:06:34 +01:00
• 9bc9ba11c5 Increase TGI benchmark tokens to 500 Lucas Armand 2026-04-30 14:04:39 -07:00
• 48fdc65e3d Update to vastai package (#84) LucasArmandVast 2026-04-14 10:41:31 -07:00
• c3baf76a9a Update to vastai package use-vastai Lucas Armand 2026-04-14 10:16:21 -07:00
• 2cd97315cd Add nltk requirement for openai worker (#83) LucasArmandVast 2026-04-13 11:30:06 -07:00
• e42afd187a pin version add-ntlk-requirement Lucas Armand 2026-04-13 11:20:45 -07:00
• 98a3182079 Add nltk requirement for openai worker Lucas Armand 2026-04-13 10:35:22 -07:00
• 4e951f4912 test vastai_sdk test package test-package Lucas Armand 2026-04-08 13:38:22 -07:00
• f636012685 add test index Lucas Armand 2026-04-08 13:18:46 -07:00
• ddb986d561 use test package Lucas Armand 2026-04-08 13:12:27 -07:00
• 99a3319e66 Point to vast-cli Lucas Armand 2026-04-08 12:30:20 -07:00
• 83c31e25a9 Add force update detection pyworker-force-update-and-retry Lucas Armand 2026-03-31 13:46:22 -07:00
• fbe1dca6fa more env_path fixes Lucas Armand 2026-03-30 16:28:51 -07:00
• 4c3120dbc5 allow override env_path Lucas Armand 2026-03-30 16:25:01 -07:00
• d7d9b915f6 allow break system packages Lucas Armand 2026-03-30 16:09:17 -07:00
• 4660b337fb Check for USE_SYSTEM_PYTHON Lucas Armand 2026-03-30 14:46:38 -07:00
• 7506ecb6b5 directly invoke one stop shop setup executable exported by vastai pip package for deployments (#82) edgaratvast 2026-03-26 10:59:49 -07:00
• ddab0d2600 directly invoke one stop shop setup executable exported by vastai pip package for deployments deployments-direct-executable Edgar Lin 2026-03-25 22:41:24 -07:00
• 62cd96ea68 Allow pre-release allow-prerelease-pip Lucas Armand 2026-03-24 13:09:04 -07:00
• 50633c5003 Update deployments script with retries. (#81) LucasArmandVast 2026-03-23 14:58:32 -07:00
• 186b388f2f Merge branch 'main' into add-hacky-deployments-script add-hacky-deployments-script Lucas Armand 2026-03-23 14:20:45 -07:00
• d1c521f973 retry S3 download Lucas Armand 2026-03-23 14:18:52 -07:00
• e1a5cf2b43 Retry until it loads Lucas Armand 2026-03-23 14:16:41 -07:00
• 2e8f18276f Add beta deployments script (#80) LucasArmandVast 2026-03-23 14:14:06 -07:00
• 87f968f961 Add hacky deployments script Lucas Armand 2026-03-23 12:39:15 -07:00
• e1529bbf9d Add new start_server.sh force-update-flag Lucas Armand 2026-02-05 17:38:55 -08:00
• eba9c480eb Merge pull request #79 from vast-ai/update-requirements Scott Darden 2026-01-14 12:07:33 -08:00
• aaca1c9645 Updated requirements to only require vastai-sdk update-requirements Lucas Armand 2026-01-14 10:47:07 -08:00
• f319db6bd5 flag for model log rotate (#78) LucasArmandVast 2026-01-12 20:03:18 -05:00
• 661d4477d6 flag for model log rotate model-log-rotation Lucas Armand 2026-01-09 14:14:37 -08:00
• 4d786b4d17 SDK Versioning Improvements (#77) LucasArmandVast 2026-01-02 13:23:07 -05:00
• 5330039cbf revert worker sdk-versioning Lucas Armand 2025-12-31 10:31:00 -08:00
• fe999dfd16 removed max_queue_time Lucas Armand 2025-12-30 10:26:57 -08:00
• 85707af107 fix name Lucas Armand 2025-12-23 18:19:35 -08:00
• 82023f1cfb add comfyui async Lucas Armand 2025-12-23 18:11:10 -08:00
• 5f9580dde2 Merge branch 'main' into sdk-versioning Lucas Armand 2025-12-22 10:12:26 -08:00
• 0b02f31aa8 Add SDK_BRANCH Lucas Armand 2025-12-22 10:09:14 -08:00
• bd3e0032a1 Add SDK version checking (#76) LucasArmandVast 2025-12-18 00:01:52 -05:00
• 3e8da87ce2 Add SDK version checking Lucas Armand 2025-12-17 20:53:28 -08:00
• e02f4bc943 Lowered concurrency of vLLM and TGI benchmarks Lucas Armand 2025-12-17 11:55:33 -08:00
• bcb04b9a32 add missing comma Lucas Armand 2025-12-17 11:40:40 -08:00
• 9daf171487 Increase queue limits for vLLM and TGI Lucas Armand 2025-12-17 11:38:55 -08:00
• 29f836eb1a Backwards compatible vLLM payload (#75) LucasArmandVast 2025-12-15 22:58:02 -05:00
• c05131cd14 explicit not None check hotfix-vllm-parsing Lucas Armand 2025-12-15 19:55:43 -08:00
• ebaf3b6d3a Add fix Lucas Armand 2025-12-15 19:51:27 -08:00
• 4380d98c01 Use PyWorker SDK (#67) LucasArmandVast 2025-12-15 22:33:03 -05:00
• 0948d7c1ab Merge branch 'main' into pyworker-sdk pyworker-sdk Lucas Armand 2025-12-15 17:24:16 -08:00
• e2bd0b1958 update readmes Lucas Armand 2025-12-15 17:14:42 -08:00
• b02ade1df5 changed to session session Lucas Armand 2025-12-15 14:23:58 -08:00
• 0b6f381dd7 Add misc Lucas Armand 2025-12-15 11:49:36 -08:00
• 74f8b6a1ef Added wheres-my-pyworker Lucas Armand 2025-12-15 10:33:44 -08:00
• fa2bf082c2 only require HF_Token on backend Lucas Armand 2025-12-12 14:47:29 -08:00