Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

main

Mono Color

• c8e9fed87a Organize public APIs (#809) Liangsheng Yin 2024-07-29 15:34:16 -07:00
• 084fa54d37 Add support for OpenAI API : offline batch(file) processing (#699) yichuan~andhnyls2002 2024-07-30 04:07:18 +08:00
• eba458bd19 Revert "Revert "fix: update flashinfer to 0.1.2 to fix sampling for cu118"" (#806) Ying Sheng 2024-07-29 12:20:42 -07:00
• 3d1cb0af83 feat: add chat template for internlm2-chat (#802) Yineng Zhang 2024-07-30 05:18:03 +10:00
• 7d352b4fdd Revert "fix: update flashinfer to 0.1.2 to fix sampling for cu118" (#805) Ying Sheng 2024-07-29 11:39:12 -07:00
• 87064015d9 fix: update flashinfer to 0.1.2 to fix sampling for cu118 (#803) Yineng Zhang 2024-07-30 04:00:52 +10:00
• 7cd4f244a4 Chunked prefill (#800) Liangsheng Yin 2024-07-29 03:32:58 -07:00
• 98111fbe3e Revert "Chunked prefill support" (#799) Ying Sheng 2024-07-29 02:38:31 -07:00
• 2ec39ab712 Chunked prefill support (#797) Liangsheng Yin 2024-07-29 02:21:50 -07:00
• 8f6274c82b Add role documentation, add system begin & end tokens (#793) ObjectNotFound 2024-07-29 14:02:49 +08:00
• 325a06c2de Fix logging (#796) Ying Sheng 2024-07-28 23:01:45 -07:00
• 79f816292e Fix lazy import location (#795) Ying Sheng 2024-07-28 22:09:50 -07:00
• b688fd858d Lazy-import third-party backends (#794) Eric Yoon 2024-07-29 13:57:41 +09:00
• 5bd899243b Update README.md (#792) Ying Sheng 2024-07-28 21:57:23 -07:00
• 8d908a937c Fix echo + lobprob for OpenAI API when the prompt is a list (#791) Ying Sheng 2024-07-28 17:09:16 -07:00
• dd7e8b9421 chore: add copyright for srt (#790) Yineng Zhang 2024-07-28 23:07:12 +10:00
• 1f013d64eb docs: make badges center (#789) Yineng Zhang 2024-07-28 22:27:52 +10:00
• 628e1fa760 docs: update README (#788) Yineng Zhang 2024-07-28 22:24:27 +10:00
• c71880f896 Vectorize logprobs computation (#787) Ying Sheng 2024-07-28 05:22:14 -07:00
• bcb6611a46 Update README.md Ying Sheng 2024-07-28 01:00:06 -07:00
• fa2aa0db0a docs: update index (#786) Yineng Zhang 2024-07-28 17:22:00 +10:00
• 6a387a69cc fix: exclude logo png in gitignore (#785) Yineng Zhang 2024-07-28 17:08:16 +10:00
• 27f5ce0a6c fix: init readthedocs support (#784) Yineng Zhang 2024-07-28 16:55:54 +10:00
• 948625799e docs: init readthedocs support (#783) Yineng Zhang 2024-07-28 16:50:31 +10:00
• 68e5262699 fix: replace pillow with PIL in PACKAGE_LIST (#781) Yineng Zhang 2024-07-28 14:06:24 +10:00
• bc1154c399 Bump version to 0.2.6 (#779) Lianmin Zheng 2024-07-27 20:29:33 -07:00
• 752e643007 Allow disabling flashinfer sampling kernel (#778) Lianmin Zheng 2024-07-27 20:18:56 -07:00
• 30db99b3d9 Rename prefill_token_logprobs -> input_token_logprobs; decode_token_logprobs -> output_token_logprobs (#776) Lianmin Zheng 2024-07-27 19:50:34 -07:00
• 0a409bd438 Fix return_log_probs with cuda graph (#775) Lianmin Zheng 2024-07-27 19:15:09 -07:00
• e4db4e5ba5 minor refactor: move check server args to server_args.py (#774) Mingyi 2024-07-27 19:03:40 -07:00
• bbc07c4197 Move sampling logits to float32 (#773) Lianmin Zheng 2024-07-27 17:30:12 -07:00
• a036d41980 Fix max new tokens (#772) Lianmin Zheng 2024-07-27 17:22:18 -07:00
• f95e661757 Fix max_tokens for OpenAI chat completion API (#766) Lianmin Zheng 2024-07-27 15:44:27 -07:00
• de854fb5c5 feat: add fake tag (#770) Yineng Zhang 2024-07-28 02:22:22 +10:00
• f64b2a9bc0 Add slack invitation link. Lianmin Zheng 2024-07-27 06:29:15 -07:00
• 9f95dcc64f Update readme (#769) Ying ShengandMingyi 2024-07-27 06:12:16 -07:00
• 0736b27020 [Minor] Improve the code style in TokenizerManager (#767) Lianmin Zheng 2024-07-27 05:05:15 -07:00
• 3fdab91912 Fix TransformerTokenizer init for chatglm2 & 3 (#761) Ke Bao 2024-07-27 17:44:46 +08:00
• ba29504b21 Update supported models (#763) Liangsheng Yin 2024-07-26 22:53:53 -07:00
• a72342f180 fix: not run workflows on fork repo (#762) Yineng Zhang 2024-07-27 14:51:33 +10:00
• c3c74bf874 docs: update model support (#760) Yineng Zhang 2024-07-27 14:07:37 +10:00
• d9fccfefe2 Fix context length (#757) Liangsheng Yin 2024-07-26 18:13:13 -07:00
• 679ebcbbdc Deepseek v2 support (#693) Liangsheng Yin 2024-07-26 17:10:07 -07:00
• 5bd06b4599 fix: use REPO_TOKEN (#755) Yineng Zhang 2024-07-27 05:56:30 +10:00
• 9a61182732 fix: add release tag workflow (#754) Yineng Zhang 2024-07-27 05:48:38 +10:00
• eeb2482186 feat: add release tag workflow (#753) Yineng Zhang 2024-07-27 05:37:02 +10:00
• 3e455b016e misc: replace deprecated variable HUGGING_FACE_HUB_TOKEN with HF_TOKEN (#752) Yineng Zhang 2024-07-27 04:19:30 +10:00
• 8628ab9c8b feat: add docker workflow (#751) Yineng Zhang 2024-07-27 03:54:51 +10:00
• 1b77670f39 chore: bump v0.2.1 (#740) Yineng Zhang 2024-07-26 21:27:41 +10:00
• 768e05d08f fix benchmark (#743) 3 people 2024-07-26 21:26:13 +10:00
• 01fbb11bb7 docs: fix typo (#742) Yineng Zhang 2024-07-26 21:05:53 +10:00
• 05d216da32 docs: add llama 3.1 405b instruction (#739) Yineng ZhangandYing1123 2024-07-26 21:03:20 +10:00
• 6b32bb1c0b misc: format (#741) Yineng Zhang 2024-07-26 21:00:51 +10:00
• 40facad5f1 feat: support token ids in /v1/completions (#736) Toshiki Kataoka 2024-07-26 18:53:17 +09:00
• da504445dc fix /generate without sampling_params (#734) Toshiki Kataoka 2024-07-26 17:27:56 +09:00
• 252e0f7bbd fix: small bug for llama-405b fp16 (#733) Ying Sheng 2024-07-25 21:14:54 -07:00
• 7f6f2f0f09 Update readme (#731) Ying Sheng 2024-07-25 09:13:37 -07:00
• 7802df1e2b Update readme Ying Sheng 2024-07-25 08:14:36 -07:00
• 1a491d00cb Bump version to 0.2.0 (#730) Ying Sheng 2024-07-25 08:03:36 -07:00
• 8fbba3de3d Fix bugs (fp8 checkpoints, triton cache manager) (#729) Ying Sheng 2024-07-25 07:42:00 -07:00
• ae0f6130cb Revert "fix: fp8 config" (#728) Ying Sheng 2024-07-25 07:25:33 -07:00
• 6010589783 misc: update bug issue template (#727) Yineng Zhang 2024-07-25 20:52:37 +10:00
• 926ac01b64 fix: resolve the logo display issue on the PyPI page (#726) Yineng Zhang 2024-07-25 20:47:46 +10:00
• 25c881a005 chore: bump v0.1.25 (#725) Yineng Zhang 2024-07-25 20:04:35 +10:00
• 04ec6ba2ac Fix dockerfile and triton cache manager (#720) Liangsheng Yin 2024-07-25 03:04:21 -07:00
• d63f13c13b fix: fp8 config (#723) Ying Sheng 2024-07-25 02:01:56 -07:00
• fded67441d misc: update bulid instruction (#724) Yineng Zhang 2024-07-25 17:08:11 +10:00
• 6e45394051 chore: add close inactive issues workflow (#722) Yineng Zhang 2024-07-25 16:31:23 +10:00
• 97e0f7d250 docs: update comment (#721) Yineng Zhang 2024-07-25 10:51:18 +10:00
• d5146baec9 docs: update supported models (#719) Yineng Zhang 2024-07-25 09:34:01 +10:00
• 459abad261 Bump version to 0.1.24 (#718) Ying Sheng 2024-07-24 15:55:01 -07:00
• 30d8e130e7 Improve benchmark scripts (#717) Ying Sheng 2024-07-24 14:44:14 -07:00
• 08a3bd19cc docs: update doc (#716) Ying Sheng 2024-07-24 13:38:06 -07:00
• 321a963b01 misc: update doc (#715) Yineng Zhang 2024-07-25 06:05:46 +10:00
• e17deb27b5 fix: llama 3.1 405b fp8 (#714) Yineng Zhang 2024-07-25 02:37:41 +10:00
• 2d3ae4e125 docs: update doc (#713) Yineng Zhang 2024-07-25 00:03:17 +10:00
• 75f4ccb7dd docs: update README (#712) Yineng Zhang 2024-07-24 23:33:28 +10:00
• 83d2b30d75 format Ying Sheng 2024-07-24 10:53:07 +00:00
• 4367f4bb8d Fix prefill size (#711) Ying Sheng 2024-07-24 03:41:15 -07:00
• 00e4baa728 Update schedule_heuristic.py Lianmin Zheng 2024-07-24 01:22:30 -07:00
• 4cd64b8ee6 Auto adjust new ratio (#708) Liangsheng Yin 2024-07-23 22:06:02 -07:00
• 01d66ae2e8 Fix multi-node deadlock (#709) Lianmin Zheng 2024-07-23 21:53:36 -07:00
• a523a3c13a Reduce hardcoded logic of kernel usage (#707) Mingyi 2024-07-23 16:42:21 -07:00
• 9f94728f5a bump version to 0.1.23 (#706) Ying Sheng 2024-07-23 13:53:19 -07:00
• 444a02441a Update vllm version to support llama3.1 (#705) Ying Sheng 2024-07-23 13:49:34 -07:00
• fa7ccb3316 feat: add e2e latency (#704) zhyncs 2024-07-24 05:51:10 +10:00
• 268684439b Use min new token ratio at start (#701) Liangsheng Yin 2024-07-23 11:52:50 -07:00
• 824a77d04d Fix hf config loading (#702) Ke Bao 2024-07-24 02:39:08 +08:00
• cf99eab7d5 Fix flashinfer (#700) Ying Sheng 2024-07-23 01:27:01 -07:00
• 9fdea29d05 misc: fix typo (#698) zhyncs 2024-07-23 02:00:27 +10:00
• df7c4c19b4 Fix trt benchmark (#697) Ying Sheng 2024-07-22 06:32:41 -07:00
• c3f1aac811 Tune params (#696) Ying Sheng 2024-07-22 03:19:24 -07:00
• d198791fe8 misc: update output token logic (#695) zhyncs 2024-07-22 19:34:05 +10:00
• c07526e46c fix: update bench serving (#694) zhyncs 2024-07-22 18:23:33 +10:00
• 7b597475f2 docs: update README (#692) zhyncs 2024-07-22 03:41:20 +10:00
• 5303c1ed22 Support Mistral-Nemo (#691) Ke Bao 2024-07-22 01:36:53 +08:00
• 65bd13386b misc: recommend to use chat model for benchmark (#690) zhyncs 2024-07-22 00:13:33 +10:00
• eedc12e12e Support Deepseek MoE Model (#689) Liangsheng Yin 2024-07-21 03:09:29 -07:00
• 5a4ef2b5c8 update readme Lianmin Zheng 2024-07-21 02:58:57 -07:00
• 9dab947d56 docs: update README (#688) zhyncs 2024-07-21 18:32:58 +10:00