Woosuk Kwon
|
89988ec8c2
|
Add Apache-2.0 license (#102)
|
2023-05-14 18:05:19 -07:00 |
|
Woosuk Kwon
|
6208d622ca
|
Minor code cleaning for SamplingParams (#99)
|
2023-05-12 18:07:09 -07:00 |
|
Woosuk Kwon
|
42f1042e1c
|
Enhance SamplingParams (#96)
|
2023-05-11 15:45:30 -07:00 |
|
Woosuk Kwon
|
55f8b0a5de
|
Implement presence and frequency penalties (#95)
|
2023-05-10 23:39:12 -07:00 |
|
Woosuk Kwon
|
9f88db35da
|
Support top-k sampling (#94)
|
2023-05-10 12:51:36 -07:00 |
|
Woosuk Kwon
|
ae356774ab
|
Avoid sorting waiting queue & Minor code cleaning (#93)
|
2023-05-10 01:57:07 -07:00 |
|
Woosuk Kwon
|
e331957784
|
Log system stats (#90)
|
2023-05-10 01:06:53 -07:00 |
|
Woosuk Kwon
|
8d66a7b6d7
|
Rename variables and methods (#91)
|
2023-05-10 00:58:31 -07:00 |
|
Woosuk Kwon
|
ce26e57fd3
|
Update sample prompts in simple_server.py (#89)
|
2023-05-09 16:47:39 -07:00 |
|
Woosuk Kwon
|
85eb631839
|
Use slow tokenizer for LLaMA (#84)
|
2023-05-09 16:03:44 -07:00 |
|
Woosuk Kwon
|
add055e151
|
Enhance model loader (#83)
|
2023-05-09 15:46:42 -07:00 |
|
Woosuk Kwon
|
7c041ab578
|
Refactor system architecture (#82)
|
2023-05-09 15:30:12 -07:00 |
|
Woosuk Kwon
|
8917782af6
|
Add a system logger (#85)
|
2023-05-08 23:03:35 -07:00 |
|
Woosuk Kwon
|
7addca5935
|
Specify python package dependencies in requirements.txt (#78)
|
2023-05-07 16:30:43 -07:00 |
|
Woosuk Kwon
|
c84e924287
|
[Minor] Fix a dtype bug (#79)
|
2023-05-06 02:12:12 -07:00 |
|
Woosuk Kwon
|
c9d5b6d4a8
|
Replace FlashAttention with xformers (#70)
|
2023-05-05 02:01:08 -07:00 |
|
Woosuk Kwon
|
189ae23133
|
Use dtype from model config & Add Dolly V2 (#63)
|
2023-05-04 03:05:37 -07:00 |
|
Woosuk Kwon
|
e548c1488a
|
Add support for GPT-2 (#60)
|
2023-05-04 02:59:56 -07:00 |
|
Woosuk Kwon
|
130d5fd8c7
|
Fix a bug in attention kernel (#68)
|
2023-05-04 02:56:09 -07:00 |
|
Woosuk Kwon
|
e070829ae8
|
Support bfloat16 data type (#54)
|
2023-05-03 14:09:44 -07:00 |
|
Woosuk Kwon
|
436e523bf1
|
Refactor attention kernels (#53)
|
2023-05-03 13:40:13 -07:00 |
|
Zhuohan Li
|
27f1410d06
|
New weight loader without np copy (#52)
|
2023-05-03 15:32:04 +08:00 |
|
Zhuohan Li
|
4858f3bb45
|
Add an option to launch cacheflow without ray (#51)
|
2023-04-30 15:42:17 +08:00 |
|
Woosuk Kwon
|
a96d63c21d
|
Add support for GPT-NeoX (Pythia) (#50)
|
2023-04-28 00:32:10 -07:00 |
|
Woosuk Kwon
|
aa50b17ca7
|
Change plotting script
|
2023-04-17 04:49:14 +00:00 |
|
Woosuk Kwon
|
0f4b32199e
|
Support various block sizes & Change default block size to 16 (#38)
|
2023-04-15 09:03:24 -07:00 |
|
Woosuk Kwon
|
84eee24e20
|
Collect system stats in scheduler & Add scripts for experiments (#30)
|
2023-04-12 15:03:49 -07:00 |
|
Siyuan (Ryans) Zhuang
|
e3cec88aa5
|
Memcpy kernel for flash attention (#29)
* optimize
* add benchmark
* add assert
* add test
|
2023-04-10 18:22:49 -07:00 |
|
Woosuk Kwon
|
b9926f7f66
|
Support block size 32 (#35)
|
2023-04-09 23:07:18 -07:00 |
|
Woosuk Kwon
|
ee88a7e5f3
|
Add an option to use dummy model weights (#33)
|
2023-04-08 23:36:12 -07:00 |
|
Woosuk Kwon
|
c267b1a02c
|
Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27)
* Add query stride to multi_query_cached_kv_attention
* Add kernel benchmark script
|
2023-04-08 13:36:09 -07:00 |
|
Woosuk Kwon
|
0f40557af6
|
Implement block copy kernel to optimize beam search (#32)
|
2023-04-07 17:45:07 -07:00 |
|
Zhuohan Li
|
a490aafa36
|
Fix potential bugs in FastAPI frontend and add comments (#28)
|
2023-04-06 13:44:24 +08:00 |
|
Woosuk Kwon
|
12659a0bd7
|
Add CUDA graph-based all reduce launcher (#26)
|
2023-04-05 11:16:57 -07:00 |
|
Siyuan (Ryans) Zhuang
|
21b3671bbc
|
Basic attention kernel that supports cached KV + (multi-)prompts (#24)
|
2023-04-04 20:34:46 -07:00 |
|
Woosuk Kwon
|
897cb2ae28
|
Optimize data movement (#20)
|
2023-04-02 00:30:17 -07:00 |
|
Zhuohan Li
|
1f01a18d39
|
Merge QKV into one linear layer (#15)
|
2023-04-02 00:23:29 -07:00 |
|
Woosuk Kwon
|
2c5cd0defe
|
Add ninja to dependency (#21)
|
2023-04-01 19:00:20 -07:00 |
|
Woosuk Kwon
|
a90c97d727
|
Use FP32 for log probabilities (#19)
|
2023-03-31 23:33:43 -07:00 |
|
Zhuohan Li
|
e3f00d191e
|
Modify README to include info on loading LLaMA (#18)
|
2023-04-01 01:07:57 +08:00 |
|
Woosuk Kwon
|
09e9245478
|
Add custom kernel for RMS normalization (#16)
|
2023-04-01 00:51:22 +08:00 |
|
Zhuohan Li
|
c45f3c3ab6
|
Optimize tensor parallel execution speed (#17)
|
2023-04-01 00:51:08 +08:00 |
|
Woosuk Kwon
|
7a7929abe8
|
Implement preemption via recomputation & Refactor scheduling logic (#12)
|
2023-03-30 14:51:46 -07:00 |
|
Woosuk Kwon
|
88c0268a18
|
Implement custom kernel for LLaMA rotary embedding (#14)
|
2023-03-30 11:04:21 -07:00 |
|
Woosuk Kwon
|
80a2f812f1
|
Implement LLaMA (#9)
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
|
2023-03-30 12:25:32 +08:00 |
|
Woosuk Kwon
|
a1b3de86cd
|
Refactor the test code for attention kernels (#13)
|
2023-03-29 18:59:27 -07:00 |
|
Woosuk Kwon
|
64e0e38314
|
Add cache watermark to avoid frequent cache eviction (#11)
|
2023-03-29 16:38:48 -07:00 |
|
Zhuohan Li
|
721fa3df15
|
FastAPI-based working frontend (#10)
|
2023-03-29 14:48:56 +08:00 |
|
Woosuk Kwon
|
d359cda5fa
|
Minor
|
2023-03-26 08:00:39 +00:00 |
|
Zhuohan Li
|
2f49f15585
|
Support tensor parallel (#2)
|
2023-03-21 13:45:42 -07:00 |
|