Ying Sheng
|
c71880f896
|
Vectorize logprobs computation (#787)
|
2024-07-28 05:22:14 -07:00 |
|
Yineng Zhang
|
948625799e
|
docs: init readthedocs support (#783)
|
2024-07-28 16:50:31 +10:00 |
|
Yineng Zhang
|
68e5262699
|
fix: replace pillow with PIL in PACKAGE_LIST (#781)
|
2024-07-28 14:06:24 +10:00 |
|
Lianmin Zheng
|
bc1154c399
|
Bump version to 0.2.6 (#779)
|
2024-07-27 20:29:33 -07:00 |
|
Lianmin Zheng
|
752e643007
|
Allow disabling flashinfer sampling kernel (#778)
|
2024-07-27 20:18:56 -07:00 |
|
Lianmin Zheng
|
30db99b3d9
|
Rename prefill_token_logprobs -> input_token_logprobs; decode_token_logprobs -> output_token_logprobs (#776)
|
2024-07-27 19:50:34 -07:00 |
|
Lianmin Zheng
|
0a409bd438
|
Fix return_log_probs with cuda graph (#775)
|
2024-07-27 19:15:09 -07:00 |
|
Mingyi
|
e4db4e5ba5
|
minor refactor: move check server args to server_args.py (#774)
|
2024-07-27 19:03:40 -07:00 |
|
Lianmin Zheng
|
bbc07c4197
|
Move sampling logits to float32 (#773)
|
2024-07-27 17:30:12 -07:00 |
|
Lianmin Zheng
|
a036d41980
|
Fix max new tokens (#772)
|
2024-07-27 17:22:18 -07:00 |
|
Lianmin Zheng
|
f95e661757
|
Fix max_tokens for OpenAI chat completion API (#766)
|
2024-07-27 15:44:27 -07:00 |
|
Lianmin Zheng
|
0736b27020
|
[Minor] Improve the code style in TokenizerManager (#767)
|
2024-07-27 05:05:15 -07:00 |
|
Ke Bao
|
3fdab91912
|
Fix TransformerTokenizer init for chatglm2 & 3 (#761)
|
2024-07-27 02:44:46 -07:00 |
|
Liangsheng Yin
|
d9fccfefe2
|
Fix context length (#757)
|
2024-07-26 18:13:13 -07:00 |
|
Liangsheng Yin
|
679ebcbbdc
|
Deepseek v2 support (#693)
|
2024-07-26 17:10:07 -07:00 |
|
Yineng Zhang
|
5bd06b4599
|
fix: use REPO_TOKEN (#755)
|
2024-07-27 05:56:30 +10:00 |
|
Yineng Zhang
|
9a61182732
|
fix: add release tag workflow (#754)
|
2024-07-27 05:48:38 +10:00 |
|
Yineng Zhang
|
eeb2482186
|
feat: add release tag workflow (#753)
|
2024-07-27 05:37:02 +10:00 |
|
Yineng Zhang
|
8628ab9c8b
|
feat: add docker workflow (#751)
|
2024-07-27 03:54:51 +10:00 |
|
Yineng Zhang
|
1b77670f39
|
chore: bump v0.2.1 (#740)
|
2024-07-26 21:27:41 +10:00 |
|
Yineng Zhang
|
768e05d08f
|
fix benchmark (#743)
Co-authored-by: hnyls2002 <hnyls2002@gmail.com>
Co-authored-by: Ying Sheng <sqy1415@gmail.com>
|
2024-07-26 21:26:13 +10:00 |
|
Yineng Zhang
|
6b32bb1c0b
|
misc: format (#741)
|
2024-07-26 21:00:51 +10:00 |
|
Toshiki Kataoka
|
40facad5f1
|
feat: support token ids in /v1/completions (#736)
|
2024-07-26 02:53:17 -07:00 |
|
Toshiki Kataoka
|
da504445dc
|
fix /generate without sampling_params (#734)
|
2024-07-26 01:27:56 -07:00 |
|
Ying Sheng
|
252e0f7bbd
|
fix: small bug for llama-405b fp16 (#733)
|
2024-07-25 21:14:54 -07:00 |
|
Ying Sheng
|
1a491d00cb
|
Bump version to 0.2.0 (#730)
|
2024-07-25 08:03:36 -07:00 |
|
Ying Sheng
|
8fbba3de3d
|
Fix bugs (fp8 checkpoints, triton cache manager) (#729)
|
2024-07-25 07:42:00 -07:00 |
|
Ying Sheng
|
ae0f6130cb
|
Revert "fix: fp8 config" (#728)
|
2024-07-25 07:25:33 -07:00 |
|
Yineng Zhang
|
926ac01b64
|
fix: resolve the logo display issue on the PyPI page (#726)
|
2024-07-25 20:47:46 +10:00 |
|
Yineng Zhang
|
25c881a005
|
chore: bump v0.1.25 (#725)
|
2024-07-25 20:04:35 +10:00 |
|
Liangsheng Yin
|
04ec6ba2ac
|
Fix dockerfile and triton cache manager (#720)
|
2024-07-25 03:04:21 -07:00 |
|
Ying Sheng
|
d63f13c13b
|
fix: fp8 config (#723)
|
2024-07-25 02:01:56 -07:00 |
|
Ying Sheng
|
459abad261
|
Bump version to 0.1.24 (#718)
|
2024-07-24 15:55:01 -07:00 |
|
Ying Sheng
|
30d8e130e7
|
Improve benchmark scripts (#717)
|
2024-07-24 14:44:14 -07:00 |
|
Yineng Zhang
|
e17deb27b5
|
fix: llama 3.1 405b fp8 (#714)
|
2024-07-24 09:37:41 -07:00 |
|
Ying Sheng
|
83d2b30d75
|
format
|
2024-07-24 10:53:07 +00:00 |
|
Ying Sheng
|
4367f4bb8d
|
Fix prefill size (#711)
|
2024-07-24 03:41:15 -07:00 |
|
Lianmin Zheng
|
00e4baa728
|
Update schedule_heuristic.py
|
2024-07-24 01:22:30 -07:00 |
|
Liangsheng Yin
|
4cd64b8ee6
|
Auto adjust new ratio (#708)
|
2024-07-23 22:06:02 -07:00 |
|
Lianmin Zheng
|
01d66ae2e8
|
Fix multi-node deadlock (#709)
|
2024-07-23 21:53:36 -07:00 |
|
Mingyi
|
a523a3c13a
|
Reduce hardcoded logic of kernel usage (#707)
|
2024-07-23 16:42:21 -07:00 |
|
Ying Sheng
|
9f94728f5a
|
bump version to 0.1.23 (#706)
|
2024-07-23 13:53:19 -07:00 |
|
Ying Sheng
|
444a02441a
|
Update vllm version to support llama3.1 (#705)
|
2024-07-23 13:49:34 -07:00 |
|
zhyncs
|
fa7ccb3316
|
feat: add e2e latency (#704)
|
2024-07-24 05:51:10 +10:00 |
|
Liangsheng Yin
|
268684439b
|
Use min new token ratio at start (#701)
|
2024-07-23 11:52:50 -07:00 |
|
Ke Bao
|
824a77d04d
|
Fix hf config loading (#702)
|
2024-07-23 11:39:08 -07:00 |
|
Ying Sheng
|
cf99eab7d5
|
Fix flashinfer (#700)
|
2024-07-23 01:27:01 -07:00 |
|
zhyncs
|
9fdea29d05
|
misc: fix typo (#698)
|
2024-07-23 02:00:27 +10:00 |
|
Ying Sheng
|
df7c4c19b4
|
Fix trt benchmark (#697)
|
2024-07-22 23:32:41 +10:00 |
|
Ying Sheng
|
c3f1aac811
|
Tune params (#696)
|
2024-07-22 03:19:24 -07:00 |
|