Skip to content

Actions: OpenRouterTeam/openrouter-runner

Actions

Release (prod)

Actions

Loading...

Show workflow options

Create status badge

release-prod.yml
43 workflow runs
43 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
deps: bump modal to 0.62.124 (#94) Release (prod) #43: Commit 34edd05 pushed by sambarnes
April 30, 2024 14:31 42s main
main
April 30, 2024 14:31 42s
fix: remove deprecated models bagel & psyfighter1 (#92) Release (prod) #42: Commit d6e2819 pushed by sambarnes
April 24, 2024 14:22 40s main
main
April 24, 2024 14:22 40s
perf: let noromaid mixtral scale to zero (#87) Release (prod) #41: Commit 5202823 pushed by sambarnes
April 8, 2024 16:07 50s main
main
April 8, 2024 16:07 50s
perf: let midnight rose scale to zero (#86) Release (prod) #40: Commit e0c3077 pushed by sambarnes
April 4, 2024 20:47 48s main
main
April 4, 2024 20:47 48s
update poetry Release (prod) #39: Commit 7301ae2 pushed by louisgv
April 4, 2024 20:14 54s main
main
April 4, 2024 20:14 54s
perf: let bagel scale to zero (#85) Release (prod) #38: Commit 9c099b3 pushed by sambarnes
April 4, 2024 18:04 46s main
main
April 4, 2024 18:04 46s
perf: reduce container idle timeout for neuralchat & psyfighter1 (#84) Release (prod) #37: Commit 54cf516 pushed by sambarnes
March 26, 2024 21:04 52s main
main
March 26, 2024 21:04 52s
perf: always keep one midnight rose (#83) Release (prod) #36: Commit af26dd5 pushed by alexanderatallah
March 23, 2024 17:11 48s main
main
March 23, 2024 17:11 48s
chore: temporarily comment out keep_warm (#82) Release (prod) #35: Commit 936f731 pushed by sambarnes
March 23, 2024 00:28 42s main
main
March 23, 2024 00:28 42s
feat: add quantize_model() fn & a MidnightRose70B (#79) Release (prod) #34: Commit 1d737c4 pushed by sambarnes
March 23, 2024 00:21 44s main
main
March 23, 2024 00:21 44s
perf: serve quantized Psyfighter2 (#81) Release (prod) #33: Commit 754d41f pushed by sambarnes
March 19, 2024 15:19 49s main
main
March 19, 2024 15:19 49s
perf: serve quantized versions of phi2, neuralchat, and psyfighter1 (… Release (prod) #32: Commit 2b1cb4a pushed by sambarnes
March 19, 2024 14:44 47s main
main
March 19, 2024 14:44 47s
perf: serve quantized versions of noromaid mixtral & bagel (#77) Release (prod) #31: Commit 1a41b87 pushed by sambarnes
March 11, 2024 17:40 48s main
main
March 11, 2024 17:40 48s
fix: revert BACKLOG_THRESHOLD from 100 back to 30 following instabili… Release (prod) #30: Commit 49f8622 pushed by sambarnes
March 8, 2024 19:24 44s main
main
March 8, 2024 19:24 44s
feat: keep_warm=1 for noromaid mixtral & bagel (#75) Release (prod) #29: Commit c22a91c pushed by sambarnes
March 8, 2024 18:17 40s main
main
March 8, 2024 18:17 40s
feat: add support for h100s & bump backlog limit (#74) Release (prod) #28: Commit db6ed5d pushed by sambarnes
March 8, 2024 14:48 45s main
main
March 8, 2024 14:48 45s
perf: bump noromaidmixtral to max_containers=3 (#73) Release (prod) #27: Commit 01b0e37 pushed by sambarnes
March 7, 2024 15:27 36s main
main
March 7, 2024 15:27 36s
fix: add a max_containers param, which controls modal concurrency_lim… Release (prod) #26: Commit 58828b5 pushed by sambarnes
March 6, 2024 18:15 38s main
main
March 6, 2024 18:15 38s
perf: move large vLLM imports into the image.imports() context manage… Release (prod) #25: Commit 2e8ea4a pushed by sambarnes
March 6, 2024 17:47 50s main
main
March 6, 2024 17:47 50s
refactor: move all models to their own unique containers (#71) Release (prod) #24: Commit 8d140f8 pushed by sambarnes
March 6, 2024 17:10 48s main
main
March 6, 2024 17:10 48s
refactor: deprecate old usage fields & simplify vllm generate fn (#68) Release (prod) #23: Commit a60f30d pushed by sambarnes
March 5, 2024 22:10 50s main
main
March 5, 2024 22:10 50s
docs: Update Docs to be more consistent. (#67) Release (prod) #22: Commit 818a299 pushed by louisgv
March 5, 2024 19:09 53s main
main
March 5, 2024 19:09 53s
feat: add finish_reason to the protocol (#70) Release (prod) #21: Commit 53541bc pushed by louisgv
February 29, 2024 07:31 1m 2s main
main
February 29, 2024 07:31 1m 2s
fix: running total of tokens for streams (#64) Release (prod) #20: Commit 04ee06f pushed by sambarnes
February 9, 2024 00:16 41s main
main
February 9, 2024 00:16 41s
Make model downloading synchronous again (#66) Release (prod) #19: Commit c751d1f pushed by alexanderatallah
February 6, 2024 01:36 36s main
main
February 6, 2024 01:36 36s