 Lianmin Zheng
|
63ba2f8d7b
|
Clean up batch data structures: Introducing ModelWorkerBatch (#1544)
|
2024-09-30 06:41:49 -07:00 |
|
|
Lianmin Zheng
|
36d5acfca5
|
Rename InputMetadata -> ForwardBatch (#1543)
|
2024-09-30 02:41:11 -07:00 |
|
|
Lianmin Zheng
|
3f0fe08d37
|
Let ModelRunner take InputMetadata as input, instead of ScheduleBatch (#1541)
|
2024-09-29 20:28:45 -07:00 |
|
|
Lianmin Zheng
|
f86c1e611f
|
Move scheduler code from tp_worker.py to scheduler.py (#1538)
|
2024-09-29 17:42:45 -07:00 |
|
|
Lianmin Zheng
|
048685430d
|
Improve process creation (#1534)
|
2024-09-29 02:36:12 -07:00 |
|
|
Lianmin Zheng
|
e165a9fc1b
|
Make detokenizer_manager.py not asyncio (#1532)
|
2024-09-28 19:33:09 -07:00 |
|
|
Lianmin Zheng
|
4e4459b91f
|
Multiple minor fixes (#1530)
|
2024-09-28 14:43:35 -07:00 |
|
|
Lianmin Zheng
|
9ae1db0bdc
|
[Fix] Ignore import error (#1513)
|
2024-09-25 11:32:21 -07:00 |
|
|
Lianmin Zheng
|
fb2d0680e0
|
[Fix] Fix clean_up_tokenization_spaces in tokenizer (#1510)
|
2024-09-24 21:37:33 -07:00 |
|
|
Lianmin Zheng
|
067d8e16fc
|
Simplify bench_latency.py (#1503)
|
2024-09-24 17:42:07 -07:00 |
|
|
Lianmin Zheng
|
28b4d8e144
|
Update test_srt_backend.py (#1502)
|
2024-09-24 03:17:10 -07:00 |
|
|
Lianmin Zheng
|
bc068e9618
|
[CI] Move AMD test to a separate file (#1500)
|
2024-09-24 02:06:28 -07:00 |
|
|
Lianmin Zheng
|
2854a5ea9f
|
Fix the overhead due to penalizer in bench_latency (#1496)
|
2024-09-23 07:38:14 -07:00 |
|
|
Lianmin Zheng
|
39bb49d156
|
Update dockerfile to include datamodel_code_generator (#1492)
|
2024-09-22 04:49:16 -07:00 |
|
|
Lianmin Zheng
|
13f1357ef0
|
Add a unit test for data parallelism (#1489)
|
2024-09-22 02:21:05 -07:00 |
|
|
Lianmin Zheng
|
167591e864
|
Better unit tests for adding a new model (#1488)
|
2024-09-22 01:50:37 -07:00 |
|
|
Lianmin Zheng
|
2cd7e181dd
|
Fix env vars in bench_latency (#1472)
|
2024-09-19 03:19:26 -07:00 |
|
|
Lianmin Zheng
|
5ce55aee15
|
Release v0.3.1.post2 (#1470)
|
2024-09-19 02:03:38 -07:00 |
|
|
Lianmin Zheng
|
2d346a57c2
|
Fix padding in the cuda graph (#1469)
|
2024-09-19 01:52:15 -07:00 |
|
|
Lianmin Zheng
|
7f24ea95c3
|
Fuse top_k and top_k in the sampler (#1457)
|
2024-09-18 04:35:35 -07:00 |
|
|
Lianmin Zheng
|
1acccb364a
|
Fix oom issues with fp8 for llama (#1454)
|
2024-09-18 03:45:19 -07:00 |
|
|
Lianmin Zheng
|
5e62a6b706
|
Add bench_server_latency.py (#1452)
|
2024-09-18 00:56:06 -07:00 |
|
|
Lianmin Zheng
|
90a26be31c
|
Release 0.3.1.post1 (#1445)
|
2024-09-17 01:47:31 -07:00 |
|
|
Lianmin Zheng
|
2fa5cec775
|
Simplify sampler and its error handling (#1441)
|
2024-09-16 21:23:31 -07:00 |
|
|
Lianmin Zheng
|
27b557aea7
|
Clean up model loader (#1440)
|
2024-09-16 18:16:27 -07:00 |
|
|
Lianmin Zheng
|
899cf5c438
|
Remove deprecated configs (#1431)
|
2024-09-15 08:52:18 -07:00 |
|
|
Lianmin Zheng
|
e79f6cd73d
|
Release v0.3.1 (#1430)
|
2024-09-15 23:03:16 +09:00 |
|
|
Lianmin Zheng
|
9ba1f09760
|
[Fix] Fix logprob and normalized_logprob (#1428)
|
2024-09-15 06:36:06 -07:00 |
|
|
Lianmin Zheng
|
282681b8a1
|
Update backend.md (#1429)
|
2024-09-15 02:55:34 -07:00 |
|
|
Lianmin Zheng
|
9463bc1385
|
Enable torch.compile for triton backend (#1422)
|
2024-09-14 15:38:37 -07:00 |
|
|
Lianmin Zheng
|
8779da95d6
|
Update pr-test.yml (#1412)
|
2024-09-13 00:37:13 -07:00 |
|
|
Lianmin Zheng
|
ad0ff62a4c
|
Balance test in CI (#1411)
|
2024-09-12 23:29:44 -07:00 |
|
|
Lianmin Zheng
|
68be2f6d3b
|
[CI] Include triton backend and online serving benchmark into CI (#1408)
|
2024-09-12 21:36:41 -07:00 |
|
|
Lianmin Zheng
|
b912de11b0
|
Make stop reason a dict instead of str (#1407)
|
2024-09-12 20:47:31 -07:00 |
|
|
Lianmin Zheng
|
3efa798116
|
Support cuda graph in the triton attention backend (#1401)
|
2024-09-12 00:36:55 -07:00 |
|
|
Lianmin Zheng
|
fec185ce0c
|
Refactor attention backend (#1381)
|
2024-09-11 11:44:26 -07:00 |
|
|
Lianmin Zheng
|
c03cece42f
|
Improve error reporting during server launch (#1390)
|
2024-09-11 04:50:04 -07:00 |
|
|
Lianmin Zheng
|
15c75e4146
|
[Fix] Fix --disable-flashinfer (#1389)
|
2024-09-11 04:36:21 -07:00 |
|
|
Lianmin Zheng
|
46094e0c1b
|
Deprecate --disable-flashinfer and introduce --attention-backend (#1380)
|
2024-09-10 17:11:16 -07:00 |
|
|
Lianmin Zheng
|
3a6e8b6d78
|
[Minor] move triton attention kernels into a separate folder (#1379)
|
2024-09-10 15:15:08 -07:00 |
|
|
Lianmin Zheng
|
6c7cb90365
|
[Minor] improve kill scripts and torchao import (#1375)
|
2024-09-11 04:27:03 +10:00 |
|
|
Lianmin Zheng
|
8d1095dbf0
|
[Docs] Improve documentations (#1368)
|
2024-09-09 20:48:28 -07:00 |
|
|
Lianmin Zheng
|
e4d68afcf0
|
[Minor] Many cleanup (#1357)
|
2024-09-09 04:14:11 -07:00 |
|
|
Lianmin Zheng
|
eda7c09048
|
Remove useless fields in global_config.py (#1328)
|
2024-09-04 05:37:32 -07:00 |
|
|
Lianmin Zheng
|
843e63d809
|
Fix the flaky test test_moe_eval_accuracy_large.py (#1326)
|
2024-09-04 04:15:11 -07:00 |
|
|
Lianmin Zheng
|
1e495e0847
|
[Fix] Fix select by ensuring each request has at least one token (#1318)
|
2024-09-03 06:31:45 -07:00 |
|
|
Lianmin Zheng
|
12cb115d38
|
Fix llama2 weight loader (#1317)
|
2024-09-03 05:32:14 -07:00 |
|
|
Lianmin Zheng
|
c500f96bb1
|
Update README.md for llava-onevision instructions (#1313)
|
2024-09-03 01:43:08 -07:00 |
|
|
Lianmin Zheng
|
f64eae3a29
|
[Fix] Reduce memory usage for loading llava model & Remove EntryClassRemapping (#1308)
|
2024-09-02 21:44:45 -07:00 |
|
|
Lianmin Zheng
|
9999442756
|
Release v0.2.15 (#1295)
|
2024-09-01 22:22:38 -07:00 |
|
|
Lianmin Zheng
|
58fa607622
|
Fix the flaky tests in test_moe_eval_accuracy_large.py (#1293)
|
2024-09-01 12:20:46 -07:00 |
|
|
Lianmin Zheng
|
761b2cebd6
|
[CI] merge all ci tests into one file (#1289)
|
2024-09-01 02:36:56 -07:00 |
|
|
Lianmin Zheng
|
1b5d56f7f8
|
[CI] Add more multi-gpu tests (#1280)
|
2024-09-01 00:27:25 -07:00 |
|
|
Lianmin Zheng
|
79ece2c51f
|
Report median instead of mean in bench_latency.py (#1269)
|
2024-08-30 06:05:01 -07:00 |
|
|
Lianmin Zheng
|
0a97d7962d
|
[Fix] Fix OOM in llava base class (#1249)
|
2024-08-28 08:45:49 -07:00 |
|
|
Lianmin Zheng
|
bf53bf5142
|
[Fix] Fix llava on multi images (#1247)
|
2024-08-28 06:33:05 -07:00 |
|
|
Lianmin Zheng
|
6c49831394
|
Add sglang.bench_latency to CI (#1243)
|
2024-08-28 21:20:54 +10:00 |
|
|
Lianmin Zheng
|
184ae1c683
|
Update README.md (#1239)
|
2024-08-28 02:15:52 -07:00 |
|
|
Lianmin Zheng
|
6cc38b2bf3
|
[Minor] Add more type annotations (#1237)
|
2024-08-28 00:54:26 -07:00 |
|
|
Lianmin Zheng
|
d3efcb3930
|
Update workflow files (#1214)
|
2024-08-25 17:45:35 -07:00 |
|
|
Lianmin Zheng
|
61bb223e0f
|
Update CI runner docs (#1213)
|
2024-08-25 17:31:52 -07:00 |
|
|
Lianmin Zheng
|
15f1a49d2d
|
Update CI workflows (#1210)
|
2024-08-25 16:43:07 -07:00 |
|
|
Lianmin Zheng
|
902278008a
|
[Minor] Improve the function organization in TokenizerManager & improve loggers (#1208)
|
2024-08-25 14:46:34 -07:00 |
|
|
Lianmin Zheng
|
bc4c7a3545
|
Relax the assert in moe throughput test to fix the flaky CI (#1207)
|
2024-08-25 10:27:02 -07:00 |
|
|
Lianmin Zheng
|
b20daf982a
|
Update README.md (#1198)
|
2024-08-24 14:50:05 -07:00 |
|
|
Lianmin Zheng
|
f6af3a6561
|
Cleanup readme, llava examples, usage examples and nccl init (#1194)
|
2024-08-24 08:02:23 -07:00 |
|
|
Lianmin Zheng
|
5623826f73
|
[Minor] Improve logging and rename the health check endpoint name (#1180)
|
2024-08-21 19:24:36 -07:00 |
|
|
Lianmin Zheng
|
bea2bb9eea
|
Improve multi-node stability (#1171)
|
2024-08-20 22:35:05 -07:00 |
|
|
Lianmin Zheng
|
a8ae640328
|
Improve docs and warnings (#1164)
|
2024-08-20 08:31:29 -07:00 |
|
|
Lianmin Zheng
|
3c1f5a9220
|
Fix duplicated imports in hf_transformers_utils.py (#1141)
|
2024-08-17 18:03:00 -07:00 |
|
|
Lianmin Zheng
|
57d0bd91ec
|
Improve benchmark (#1140)
|
2024-08-17 17:43:23 -07:00 |
|
|
Lianmin Zheng
|
cdc8d60752
|
Improve the code style: more comments and remove useless packages (#1139)
|
2024-08-17 14:37:52 -07:00 |
|
|
Lianmin Zheng
|
5a261bd055
|
Fix the deadlock in multi-node tp (#1122)
|
2024-08-16 01:39:24 -07:00 |
|
|
Lianmin Zheng
|
87a0db82b8
|
update hyperparameter guide (#1114)
|
2024-08-15 10:54:24 -07:00 |
|
|
Lianmin Zheng
|
0cb099e20a
|
set CUDA_DEVICE_MAX_CONNECTIONS=1 (#1113)
|
2024-08-16 03:47:39 +10:00 |
|
|
Lianmin Zheng
|
e86b1ccbf0
|
Enable chunked prefill by default (#1040)
|
2024-08-14 21:56:20 -07:00 |
|
|
Lianmin Zheng
|
326df4bab2
|
Use a single workspace for flashinfer (#1077)
|
2024-08-14 19:25:37 -07:00 |
|
|
Lianmin Zheng
|
a59636bb5e
|
Update grok 1 model (#1095)
|
2024-08-14 04:40:44 -07:00 |
|
|
Lianmin Zheng
|
8f790ac100
|
Fix a bug in cuda graph runner (#1094)
|
2024-08-14 03:25:38 -07:00 |
|
|
Lianmin Zheng
|
ad3e4f1619
|
Update the mixtral to use the better FusedMoE layer (#1081)
|
2024-08-13 15:44:25 -07:00 |
|
|
Lianmin Zheng
|
c877292cc1
|
Re-organize CI tests (#1052)
|
2024-08-12 03:39:01 -07:00 |
|
|
Lianmin Zheng
|
0c1c72a0b4
|
Fix accuracy test (#1051)
|
2024-08-12 19:48:40 +10:00 |
|
|
Lianmin Zheng
|
41598e0d8e
|
Add longer accuracy test on CI (#1049)
|
2024-08-12 09:21:38 +00:00 |
|
|
Lianmin Zheng
|
fb1f28cbbb
|
Clean up the comments and names under python/sglang/srt/layers (#1047)
|
2024-08-12 05:54:37 +00:00 |
|
|
Lianmin Zheng
|
14b6493087
|
Delete the useless test/srt/test_throughput.py (#1045)
|
2024-08-11 21:31:52 -07:00 |
|
|
Lianmin Zheng
|
8207637029
|
Improve end-to-end throughput test and its coverage (#1039)
|
2024-08-11 18:27:33 -07:00 |
|
|
Lianmin Zheng
|
d84c5e70f7
|
Test the case when max_new_tokens is very large (#1038)
|
2024-08-11 16:41:03 -07:00 |
|
|
Lianmin Zheng
|
d785412077
|
Fix the case when max_new_tokens is too large (#1025)
|
2024-08-11 15:20:18 -07:00 |
|
|
Lianmin Zheng
|
4080e82244
|
Fix the case where r.prefix_indices is None (#1031)
|
2024-08-11 04:53:51 -07:00 |
|
|
Lianmin Zheng
|
9dae407812
|
Improve type annotation (#1029)
|
2024-08-11 02:44:59 -07:00 |
|
|
Lianmin Zheng
|
a97df79124
|
Clean up readme and arguments of chunked prefill (#1022)
|
2024-08-11 01:18:52 -07:00 |
|
|
Lianmin Zheng
|
54fb1c80c0
|
Clean up unit tests (#1020)
|
2024-08-10 15:09:03 -07:00 |
|
|
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 |
|
|
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
|
f64b2a9bc0
|
Add slack invitation link.
|
2024-07-27 06:29:15 -07:00 |
|