SangBin Cho and GitHub
6a0f617210
[Core] Fix circular reference which leaked llm instance in local dev env ( #4737 )
...
Storing exception frame is extremely prone to circular refernece because it contains the reference to objects.
When tensorizer is not installed, it leaks llm instance because error frame has references to various modules which cause circular reference problem.
I also found spec decoding has a circular reference issue, and I solved it using weakref.proxy.
2024-05-10 23:54:32 +09:00
43c413ec57
[Kernel] Use flashinfer for decoding ( #4353 )
...
Co-authored-by: LiuXiaoxuanPKU <llilyliupku@gmail.com >
2024-05-03 15:51:27 -07:00
SangBin Cho and GitHub
0f8a91401c
[Core] Ignore infeasible swap requests. ( #4557 )
2024-05-02 14:31:20 -07:00
SangBin Cho and GitHub
0d62fe58db
[Bug fix][Core] assert num_new_tokens == 1 fails when SamplingParams.n is not 1 and max_tokens is large & Add tests for preemption ( #4451 )
2024-05-01 19:24:13 -07:00
SangBin Cho and GitHub
36729bac13
[Test] Test multiple attn backend for chunked prefill. ( #4023 )
2024-04-12 09:56:57 -07:00
e42df7227d
[Test] Add xformer and flash attn tests ( #3961 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com >
2024-04-11 03:09:50 +00:00
SangBin Cho and GitHub
67b4221a61
[Core][5/N] Fully working chunked prefill e2e ( #3884 )
2024-04-10 17:56:48 -07:00
26422e477b
[Test] Make model tests run again and remove --forked from pytest ( #3631 )
...
Co-authored-by: Simon Mo <simon.mo@hey.com >
2024-03-28 21:06:40 -07:00
SangBin Cho and GitHub
6e435de766
[1/n][Chunked Prefill] Refactor input query shapes ( #3236 )
2024-03-20 14:46:05 -07:00
Zhuohan Li and GitHub
a61f0521b8
[Test] Add basic correctness test ( #2908 )
2024-02-18 16:44:50 -08:00
