Commit Graph

  • c70f85992c ci: reduce machine type to more available options Aaron Pham 2024-06-11 09:45:12 -04:00
  • 7bccecd2f0 fix(ci): specifying network_id from secrets Aaron Pham 2024-06-11 09:42:05 -04:00
  • d43acd6f98 chore(tests): increase timeout tenfold Aaron Pham 2024-06-11 09:40:17 -04:00
  • 7116c69da5 fix: masks shells Aaron Pham 2024-06-11 09:34:52 -04:00
  • 6cdcb0d20a chore(infra): add masks Aaron Pham 2024-06-11 09:32:16 -04:00
  • eaf5dafca9 feat(infra): add support for autogenerate CI runners Aaron Pham 2024-06-11 09:27:09 -04:00
  • a5995a6bb8 chore: remove bloated echo Aaron Pham 2024-06-11 10:26:45 +00:00
  • c14071736f chore: update scripts to simplify workload [skip ci] Aaron Pham 2024-06-11 06:24:29 -04:00
  • 59c184be18 fix(ci): set absolute path for nix for non-interactive shell Aaron Pham 2024-06-11 09:56:25 +00:00
  • 40403b2026 chore(tests): use smaller models for faster load time Aaron Pham 2024-06-11 09:52:56 +00:00
  • ff92292004 ci: pre-commit autoupdate [pre-commit.ci] (#1012) [skip ci] pre-commit-ci[bot] 2024-06-11 04:16:45 -04:00
  • a2ef7fccdc chore(deps-dev): bump braces from 3.0.2 to 3.0.3 (#1013) [skip ci] dependabot[bot] 2024-06-11 04:16:29 -04:00
  • 6ca39486a0 feat(nix): reproducible scripts [skip ci] Aaron Pham 2024-06-11 08:10:26 +00:00
  • 4f64649fe4 feat: add support for tests mode on daemon. Aaron Pham 2024-06-11 08:01:21 +00:00
  • b1a879e0e5 chore(infra): ignore default command to speed up dev [skip ci] Aaron Pham 2024-06-11 07:36:52 +00:00
  • 3e47c2dd5d feat: add support to run tests directly Aaron Pham 2024-06-11 07:33:45 +00:00
  • b365e2dd20 infra: add instructions on local.sh dev Aaron Pham 2024-06-11 07:21:24 +00:00
  • ca306adde7 infra: update installation deps Aaron Pham 2024-06-11 05:44:32 +00:00
  • 1abc44d4bc chore(deps): bump taiki-e/install-action from 2.34.0 to 2.38.0 (#1011) dependabot[bot] 2024-06-11 01:10:48 -04:00
  • 41ad0a9b01 chore: bump vllm to 0.4.3 Aaron Pham 2024-06-10 22:21:19 -04:00
  • bcecbbd918 chore: bump vllm to 0.4.3 Zhao Shenyang 2024-06-11 03:20:20 +08:00
  • 7a442f2104 Merge pull request #1 from bentoml/rick-0604-pr-chat-template Rick Zhou 2024-06-09 16:03:03 -07:00
  • 4ec0b388e9 fix(infra): fix template to export [skip ci] [generated] Aaron Pham 2024-06-09 07:58:29 -04:00
  • 3c7362289a chore(infra): cleanup bashscript and respect .envrc [skip ci] Aaron Pham 2024-06-08 01:08:43 -04:00
  • 5d97ef604b fix: ensure process exit bojiang 2024-06-08 01:21:40 +08:00
  • 1545a6ae80 fix: terminate subprocess bojiang 2024-06-07 14:21:38 +08:00
  • 69597378e7 Delete outlines-integration directory bojiang 2024-06-07 11:59:10 +08:00
  • 81c12a42f6 add qwen bojiang 2024-06-07 11:55:27 +08:00
  • acdeafef48 stop stream server log when ready bojiang 2024-06-07 09:46:03 +08:00
  • ac0eb04867 chore: stream output for background commands bojiang 2024-06-06 14:42:16 +08:00
  • a0bda52299 add source_repo bojiang 2024-06-05 13:40:43 +08:00
  • 82449f42d3 docs: update README.md (#1008) Aaron Pham 2024-06-04 18:25:15 -04:00
  • cbde63ab24 feat: Use community chat template as the source of truth. Fall back to HF tokenizer template Rick Zhou 2024-06-04 21:21:12 +00:00
  • 091829a830 support Python>=3.9 bojiang 2024-06-04 22:50:10 +08:00
  • ed55f29011 support Python 3.9 bojiang 2024-06-04 22:27:05 +08:00
  • 35e4181d90 support platforms filter bojiang 2024-06-04 21:22:31 +08:00
  • a1397bb20b Update README.md bojiang 2024-06-04 20:53:18 +08:00
  • 64b22098c7 ask for updating repo bojiang 2024-06-04 20:50:46 +08:00
  • d58aff9e02 only list first alias bojiang 2024-06-04 20:31:52 +08:00
  • 810ba16703 match instance type bojiang 2024-06-04 20:17:45 +08:00
  • 9d667bb46a add more version of llama bojiang 2024-06-04 19:54:26 +08:00
  • 47fefe30ed chattts bojiang 2024-06-03 17:25:32 +08:00
  • cd7c0e2c20 deployment target bojiang 2024-05-30 20:26:56 +08:00
  • 10a60307c1 infra: prepare for release 0.5.5 [generated] [skip ci] v0.5.5 Aaron Pham 2024-06-03 22:14:58 +00:00
  • fe17a235ce chore(ci): prepare for releases Aaron Pham 2024-06-03 17:09:18 -04:00
  • a2746a6ff2 fix(client): generate config from model_name to avoid private model Aaron Pham 2024-06-03 16:53:08 -04:00
  • 295bfcb589 chore(deps): bump taiki-e/install-action from 2.33.34 to 2.34.0 (#1006) dependabot[bot] 2024-06-03 16:46:13 -04:00
  • 15cada079a fix(models): make sure to use private-tag name for the generated service paperspace 2024-06-03 20:45:17 +00:00
  • 9ba895848f fix(core): makes quantise optional paperspace 2024-06-03 17:42:05 +00:00
  • 27c544d073 ci: pre-commit autoupdate [pre-commit.ci] (#1007) pre-commit-ci[bot] 2024-06-03 13:36:19 -04:00
  • 8f27daa058 Update openvllm protocol to be compatible with 0.4.2 Rick Zhou 2024-06-03 08:15:22 +00:00
  • 2b15aaee96 fix: remove breakpoint paperspace 2024-06-02 22:29:12 +00:00
  • c60398c45b chore: add more info to metadata Aaron Pham 2024-06-02 17:57:51 -04:00
  • 3193190b94 chore: update configuration to yield objects instead Aaron Pham 2024-06-02 17:48:03 -04:00
  • 9d3ddae520 fix(client): remove circular dependency Aaron Pham 2024-06-02 12:31:08 -04:00
  • 7d563ee121 chore(ci): update scripts [skip ci] paperspace 2024-06-02 16:12:20 +00:00
  • 30dc280006 chore(ci): update pnpm-lock.yaml [skip ci] Aaron Pham 2024-06-02 12:01:38 -04:00
  • a93da12084 chore: upgrade to new vLLM schema paperspace 2024-06-02 15:52:45 +00:00
  • 2e7592cd45 fix(ci): no need to install default packages paperspace 2024-06-02 14:27:54 +00:00
  • 8fea50dfdb feat: update ROCm check for syspath paperspace 2024-06-02 14:20:23 +00:00
  • bf28f977bc feat(models): command-r (#1005) Aaron Pham 2024-06-02 10:16:08 -04:00
  • 9649073713 infra: prepare for release 0.5.4 [generated] [skip ci] v0.5.4 Aaron Pham 2024-06-01 00:37:27 +00:00
  • 45aceb172f feat(API): add light support for batch inference (#1004) Aaron Pham 2024-05-31 20:36:12 -04:00
  • b165d94fbb Create README.md bojiang 2024-05-31 23:04:18 +08:00
  • 91cdc6641a rm README bojiang 2024-05-31 22:50:08 +08:00
  • 5df10f7ea1 ignore ChatTTS bojiang 2024-05-31 22:49:40 +08:00
  • 5e67ca4dcf fix chattts bojiang 2024-05-31 22:48:13 +08:00
  • b8467aa09e use absolute path bojiang 2024-05-31 21:44:47 +08:00
  • a3cc7544d8 add chattts bojiang 2024-05-31 21:19:16 +08:00
  • 162458ffe6 infra: prepare for release 0.5.3 [generated] [skip ci] v0.5.3 Aaron Pham 2024-05-30 21:30:21 +00:00
  • 12f0d45a9d fix(client): make sure to initialised helpers class correctly Aaron Pham 2024-05-30 17:26:09 -04:00
  • 2099f3a6f2 pre select bento bojiang 2024-05-30 14:03:22 +08:00
  • 6be3377c83 use pure python git bojiang 2024-05-30 11:55:06 +08:00
  • c94a2e0cb0 clean bojiang 2024-05-29 09:54:09 +08:00
  • 49908ec289 infra: prepare for release 0.5.2 [generated] [skip ci] v0.5.2 Aaron Pham 2024-05-29 04:44:59 +00:00
  • 7fca472a66 chore: update readme [skip ci] paperspace 2024-05-29 04:43:50 +00:00
  • e9e46b2cc7 chore: update examples and readme Aaron Pham 2024-05-29 00:41:32 -04:00
  • 02010d3499 fix: synchronize into llm_config dict paperspace 2024-05-29 04:31:34 +00:00
  • ef11e54a6d chore: update docs and base instruction [skip ci] paperspace 2024-05-29 03:19:47 +00:00
  • 439f10c786 chore(ci): make sure binary depends on publish to avoid race condition Aaron Pham 2024-05-28 22:48:08 -04:00
  • 5ff77d1f6e infra: prepare for release 0.5.1 [generated] [skip ci] v0.5.1 Aaron Pham 2024-05-29 02:44:23 +00:00
  • c820cececb fix(generate): make sure to only pass prompt_token_ids if it is a valid mutable paperspace 2024-05-29 02:42:13 +00:00
  • fd527352b2 chore(ci): cleanup unnecessary dev refresh cycle Aaron Pham 2024-05-27 14:34:33 -04:00
  • 2314a3667e infra: prepare for release 0.5.0 [generated] [skip ci] v0.5.0 Aaron Pham 2024-05-27 18:20:30 +00:00
  • cc1b23da57 ci: final check for releases [skip ci] paperspace 2024-05-27 18:19:03 +00:00
  • fc01ad71ea ci: pre-commit autoupdate [pre-commit.ci] [skip ci] (#1002) pre-commit-ci[bot] 2024-05-27 14:09:26 -04:00
  • ed868bad5c chore: update releases script Aaron Pham (mbp16) 2024-05-27 14:05:42 -04:00
  • 9da0b4134c chore(qol): make envvar private paperspace 2024-05-27 18:07:24 +00:00
  • a4a6060f69 infra: prepare for release 0.5.0-alpha.15 [generated] [skip ci] v0.5.0-alpha.15 Aaron Pham 2024-05-27 17:53:45 +00:00
  • 07655c9ba8 chore(build): remove vllm_version envvar and lock into templates paperspace 2024-05-27 17:49:58 +00:00
  • ba5a5da720 chore: udpate docstring paperspace 2024-05-27 17:02:26 +00:00
  • 0f32290606 chore(packages): ready for 0.5 releases paperspace 2024-05-27 16:54:53 +00:00
  • 20ac656018 fix(deps): make sure core deps are available on setup Aaron Pham (mbp16) 2024-05-27 12:44:22 -04:00
  • f4f7f16e81 chore(releases): remove deadcode Aaron Pham (mbp16) 2024-05-27 12:37:50 -04:00
  • da42c269c9 fix(ci): remove checking for hatch Aaron Pham (mbp16) 2024-05-27 12:12:40 -04:00
  • 5fcfa51573 chore(deps): bump taiki-e/install-action from 2.33.22 to 2.33.34 (#1000) dependabot[bot] 2024-05-27 11:59:51 -04:00
  • e84cd815e4 fix(releases): make sure to use correct hash paperspace 2024-05-27 15:59:09 +00:00
  • 1eea284810 chore: update actions to v5 paperspace 2024-05-27 15:52:38 +00:00
  • 43439f7784 chore: list models in tree view bojiang 2024-05-27 18:23:40 +08:00
  • a385e3262f fix: replace gemma 7b awq chat_template bojiang 2024-05-27 18:16:52 +08:00