Commits · de23687d168ebeaa8872c27f05b8292bab0fac71 · norm / vllm

19 Nov, 2023 1 commit
- [Optimization] Implement fused add rmsnorm (#1667) · e1054247
  ljss authored Nov 19, 2023
  
  e1054247
03 Nov, 2023 1 commit

Antoni Baum authored Nov 03, 2023


Signed-off-by: Antoni Baum <antoni.baum@protonmail.com>
Co-authored-by: Viktor Ferenczi <viktor@ferenczi.eu>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

9f669a9a

31 Oct, 2023 1 commit
- Fix integer overflows in attention & cache ops (#1514) · 0ce8647d
  Woosuk Kwon authored Oct 31, 2023
  
  0ce8647d
22 Oct, 2023 1 commit

Support SqueezeLLM (#1326) · 1f24755b

chooper1 authored Oct 22, 2023


Co-authored-by: squeeze-ai-lab <squeezeailab.bair@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

1f24755b

17 Oct, 2023 1 commit
- Change scheduler & input tensor shape (#1381) · c1376e0f
  Woosuk Kwon authored Oct 16, 2023
  
  c1376e0f
16 Oct, 2023 2 commits
- Implement PagedAttention V2 (#1348) · 928de468
  Woosuk Kwon authored Oct 16, 2023
  
  928de468
- Minor fix on AWQ kernel launch (#1356) · 29678cd2
  Woosuk Kwon authored Oct 15, 2023
  
  29678cd2
11 Oct, 2023 2 commits
- Fix overflow in awq kernel (#1295) · 980dd4a2
  CHU Tianxiang authored Oct 11, 2023
```
Co-authored-by: 楚天翔 <tianxiang.ctx@alibaba-inc.com>
```
  980dd4a2
- workaround of AWQ for Turing GPUs (#1252) · 82857368
  twaka authored Oct 11, 2023
  
  82857368
01 Oct, 2023 1 commit
- Fix boundary check in paged attention kernel (#1241) · ebe4d1db
  Liang authored Oct 02, 2023
  
  ebe4d1db
27 Sep, 2023 1 commit
- Allocate more shared memory to attention kernel (#1154) · cf5cb1e3
  Antoni Baum authored Sep 26, 2023
  
  cf5cb1e3
18 Sep, 2023 1 commit
- Add minimum capability requirement for AWQ (#1064) · 2b1c116b
  Woosuk Kwon authored Sep 18, 2023
  
  2b1c116b
16 Sep, 2023 1 commit

Implement AWQ quantization support for LLaMA (#1032) · e3e79e9e

Woosuk Kwon authored Sep 16, 2023


Co-authored-by: Robert Irvine <robert@seamlessml.com>
Co-authored-by: root <rirv938@gmail.com>
Co-authored-by: Casper <casperbh.96@gmail.com>
Co-authored-by: julian-q <julianhquevedo@gmail.com>

e3e79e9e

07 Sep, 2023 1 commit

[FIX] Fix Alibi implementation in PagedAttention kernel (#945) · db09d4ad

Zhuohan Li authored Sep 07, 2023



* [FIX] Fix Alibi implementation in PagedAttention kernel

* Fix test_attention

* Fix

---------
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Oliver-ss <yuansongwx@outlook.com>

db09d4ad

06 Sep, 2023 1 commit
- [BugFix] Implement RoPE for GPT-J (#941) · 320a622e
  Woosuk Kwon authored Sep 06, 2023
  
  320a622e
04 Sep, 2023 1 commit
- [BugFix] Fix NaN errors in paged attention kernel (#936) · bf87484e
  Woosuk Kwon authored Sep 04, 2023
  
  bf87484e
02 Sep, 2023 1 commit
- Avoid compiling kernels for double data type (#933) · 8ce9c50d
  Woosuk Kwon authored Sep 02, 2023
  
  8ce9c50d
22 Aug, 2023 1 commit
- Implement approximate GELU kernels (#828) · d64bf164
  Woosuk Kwon authored Aug 23, 2023
  
  d64bf164
04 Aug, 2023 1 commit
- [OPTIMIZATION] Optimizes the single_query_cached_kv_attention kernel (#420) · 79af7e96
  Dean Leitersdorf authored Aug 04, 2023
  
  79af7e96
02 Aug, 2023 1 commit
- Add Falcon support (new) (#592) · 1b0bd0fe
  Zhuohan Li authored Aug 02, 2023
  
  1b0bd0fe
20 Jul, 2023 1 commit
- Add support for LLaMA-2 (#505) · 6fc2a38b
  Zhuohan Li authored Jul 20, 2023
  
  6fc2a38b
15 Jul, 2023 1 commit
- Optimize MQA Kernel (#452) · 96853af5
  Zhuohan Li authored Jul 14, 2023
  
  96853af5
09 Jul, 2023 1 commit
- [Model] Add support for GPT-J (#226) · c8948361
  Andre Slavescu authored Jul 08, 2023
```
Co-authored-by: woWoosuk Kwon <woosuk.kwon@berkeley.edu>
```
  c8948361
03 Jul, 2023 2 commits
- [Model] Add support for MPT (#334) · 404422f4
  Woosuk Kwon authored Jul 03, 2023
  
  404422f4
- Add support for BLOOM (#331) · e41f0670
  Woosuk Kwon authored Jul 03, 2023
  
  e41f0670
17 Jun, 2023 1 commit
- Change the name to vLLM (#150) · 0b98ba15
  Woosuk Kwon authored Jun 17, 2023
  
  0b98ba15
07 Jun, 2023 1 commit
- Support FP32 (#141) · e38074b1
  Woosuk Kwon authored Jun 07, 2023
  
  e38074b1
27 May, 2023 1 commit
- Improve setup script & Add a guard for bfloat16 kernels (#130) · d7211684
  Woosuk Kwon authored May 27, 2023
  
  d7211684
15 May, 2023 1 commit
- Add copyright headers to source files adapted from FT (#104) · 667ba399
  Woosuk Kwon authored May 14, 2023
  
  667ba399
04 May, 2023 1 commit
- Fix a bug in attention kernel (#68) · 130d5fd8
  Woosuk Kwon authored May 04, 2023
  
  130d5fd8
03 May, 2023 2 commits
- Support bfloat16 data type (#54) · e070829a
  Woosuk Kwon authored May 03, 2023
  
  e070829a
- Refactor attention kernels (#53) · 436e523b
  Woosuk Kwon authored May 03, 2023
  
  436e523b
28 Apr, 2023 1 commit
- Add support for GPT-NeoX (Pythia) (#50) · a96d63c2
  Woosuk Kwon authored Apr 28, 2023
  
  a96d63c2
15 Apr, 2023 1 commit
- Support various block sizes & Change default block size to 16 (#38) · 0f4b3219
  Woosuk Kwon authored Apr 15, 2023
  
  0f4b3219
11 Apr, 2023 1 commit
- Memcpy kernel for flash attention (#29) · e3cec88a
  Siyuan (Ryans) Zhuang authored Apr 10, 2023
```
* optimize

* add benchmark

* add assert

* add test
```
  e3cec88a
10 Apr, 2023 1 commit
- Support block size 32 (#35) · b9926f7f
  Woosuk Kwon authored Apr 09, 2023
  
  b9926f7f
08 Apr, 2023 2 commits
- Add query stride to multi_query_cached_kv_attention & Add kernel benchmark script (#27) · c267b1a0
  Woosuk Kwon authored Apr 08, 2023
```
* Add query stride to multi_query_cached_kv_attention

* Add kernel benchmark script
```
  c267b1a0
- Implement block copy kernel to optimize beam search (#32) · 0f40557a
  Woosuk Kwon authored Apr 07, 2023
  
  0f40557a
05 Apr, 2023 1 commit
- Basic attention kernel that supports cached KV + (multi-)prompts (#24) · 21b3671b
  Siyuan (Ryans) Zhuang authored Apr 04, 2023
  
  21b3671b
02 Apr, 2023 1 commit
- Optimize data movement (#20) · 897cb2ae
  Woosuk Kwon authored Apr 02, 2023
  
  897cb2ae