583 Commits

Author SHA1 Message Date
Woosuk Kwon
c3372e87be
Remove dependency on CuPy (#2152) 2023-12-17 01:49:07 -08:00
Woosuk Kwon
b0a1d667b0
Pin PyTorch & xformers versions (#2155) 2023-12-17 01:46:54 -08:00
Woosuk Kwon
e1d5402238
Fix all-reduce memory usage (#2151) 2023-12-17 01:44:45 -08:00
Woosuk Kwon
3d1cfbfc74
[Minor] Delete Llama tokenizer warnings (#2146) 2023-12-16 22:05:18 -08:00
Woosuk Kwon
37ca558103
Optimize model execution with CUDA graph (#1926)
Co-authored-by: Chen Shen <scv119@gmail.com>
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>
2023-12-16 21:12:08 -08:00
Roy
eed74a558f
Simplify weight loading logic (#2133) 2023-12-16 12:41:23 -08:00
Woosuk Kwon
2acd76f346
[ROCm] Temporarily remove GPTQ ROCm support (#2138) 2023-12-15 17:13:58 -08:00
Woosuk Kwon
b81a6a6bb3
[Docs] Add supported quantization methods to docs (#2135) 2023-12-15 13:29:22 -08:00
CHU Tianxiang
0fbfc4b81b
Add GPTQ support (#916) 2023-12-15 03:04:22 -08:00
Yunfeng Bai
c06170cc8e
Add a flag to include stop string in output text (#1976) 2023-12-15 00:45:58 -08:00
Mingcan Xiang
614856da25
Avoid multiple redefinition (#1817) 2023-12-14 09:35:58 -08:00
TJian
05bdf4eaf3
Fix Dockerfile.rocm (#2101)
Co-authored-by: miloice <jeffaw99@hotmail.com>
2023-12-14 00:45:58 -08:00
mezuzza
6774bd50b0
Fix typing in AsyncLLMEngine & add toml to requirements-dev (#2100) 2023-12-14 00:19:41 -08:00
Woosuk Kwon
31c1f3255e
Bump up to v0.2.5 (#2095) v0.2.5 2023-12-13 23:56:15 -08:00
Antoni Baum
21d93c140d
Optimize Mixtral with expert parallelism (#2090) 2023-12-13 23:55:07 -08:00
Woosuk Kwon
f1c8520146
[BugFix] Fix input positions for long context with sliding window (#2088) 2023-12-13 12:28:13 -08:00
Woosuk Kwon
096827c284
[Docs] Add notes on ROCm-supported models (#2087) 2023-12-13 09:45:34 -08:00
Woosuk Kwon
6565d9e33e
Update installation instruction for vLLM + CUDA 11.8 (#2086) 2023-12-13 09:25:59 -08:00
TJian
f375ec8440
[ROCm] Upgrade xformers version for ROCm & update doc (#2079)
Co-authored-by: miloice <jeffaw99@hotmail.com>
2023-12-13 00:56:05 -08:00
Woosuk Kwon
518369d78c
Implement lazy model loader (#2044) 2023-12-12 22:21:45 -08:00
Woosuk Kwon
30bad5c492
Fix peak memory profiling (#2031) 2023-12-12 22:01:53 -08:00
Simon Mo
3fefe271ec
Update Dockerfile to build Megablocks (#2042) 2023-12-12 17:34:17 -08:00
Megha Agarwal
6428f1d051
Support MPT with GQA (#1938)
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2023-12-12 10:16:05 -08:00
Woosuk Kwon
7e1b21daac
Remove einops from requirements (#2049) 2023-12-12 09:34:09 -08:00
Woosuk Kwon
cb3f30c600
Upgrade transformers version to 4.36.0 (#2046) 2023-12-11 18:39:14 -08:00
Woosuk Kwon
f3e024bece
[CI/CD] Upgrade PyTorch version to v2.1.1 (#2045) 2023-12-11 17:48:11 -08:00
Woosuk Kwon
31d2ab4aff
Remove python 3.10 requirement (#2040) 2023-12-11 12:26:42 -08:00
Simon Mo
eb17212858
Update Dockerfile to support Mixtral (#2027) 2023-12-11 11:59:08 -08:00
Woosuk Kwon
4dd4b5c538
Bump up to v0.2.4 (#2034) v0.2.4 2023-12-11 11:49:39 -08:00
Woosuk Kwon
6120e5aaea
Fix import error msg for megablocks (#2038) 2023-12-11 11:40:56 -08:00
Ram
2eaa81b236
Update README.md to add megablocks requirement for mixtral (#2033) 2023-12-11 11:37:34 -08:00
Woosuk Kwon
81ce2a4b26
[Minor] Fix type annotation in Mixtral (#2036) 2023-12-11 11:32:39 -08:00
Woosuk Kwon
5dd80d3777
Fix latency benchmark script (#2035) 2023-12-11 11:19:08 -08:00
Woosuk Kwon
beeee69bc9
Revert adding Megablocks (#2030) 2023-12-11 10:49:00 -08:00
Ram
9bf28d0b69
Update requirements.txt for mixtral (#2029) 2023-12-11 10:39:29 -08:00
Ikko Eltociear Ashimine
c0ce15dfb2
Update run_on_sky.rst (#2025)
sharable -> shareable
2023-12-11 10:32:58 -08:00
Woosuk Kwon
b9bcdc7158
Change the load format to pt for Mixtral (#2028) 2023-12-11 10:32:17 -08:00
Woosuk Kwon
4ff0203987
Minor fixes for Mixtral (#2015) 2023-12-11 09:16:15 -08:00
Pierre Stock
b5f882cc98
Mixtral 8x7B support (#2011)
Co-authored-by: Pierre Stock <p@mistral.ai>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2023-12-11 01:09:15 -08:00
Simon Mo
2e8fc0d4c3
Fix completion API echo and logprob combo (#1992) 2023-12-10 13:20:30 -08:00
wbn
dacaf5a400
Replace head_mapping params with num_kv_heads to attention kernel. (#1997)
Co-authored-by: wangguoya <wangguoya@baidu.com>
Co-authored-by: Yang Zhao <zhaoyangstar@foxmail.com>
2023-12-10 10:12:53 -08:00
Woosuk Kwon
24cde76a15
[Minor] Add comment on skipping rope caches (#2004) 2023-12-10 10:04:12 -08:00
Jin Shang
1aa1361510
Fix OpenAI server completion_tokens referenced before assignment (#1996) 2023-12-09 21:01:21 -08:00
Woosuk Kwon
fe470ae5ad
[Minor] Fix code style for baichuan (#2003) 2023-12-09 19:24:29 -08:00
Jun Gao
3a8c2381f7
Fix for KeyError on Loading LLaMA (#1978) 2023-12-09 15:59:57 -08:00
Simon Mo
c85b80c2b6
[Docker] Add cuda arch list as build option (#1950) 2023-12-08 09:53:47 -08:00
firebook
2b981012a6
Fix Baichuan2-7B-Chat (#1987) 2023-12-08 09:38:36 -08:00
TJian
6ccc0bfffb
Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836)
Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Amir Balwel <amoooori04@gmail.com>
Co-authored-by: root <kuanfu.liu@akirakan.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: kuanfu <kuanfu.liu@embeddedllm.com>
Co-authored-by: miloice <17350011+kliuae@users.noreply.github.com>
2023-12-07 23:16:52 -08:00
Daya Khudia
c8e7eb1eb3
fix typo in getenv call (#1972) 2023-12-07 16:04:41 -08:00
AguirreNicolas
24f60a54f4
[Docker] Adding number of nvcc_threads during build as envar (#1893) 2023-12-07 11:00:32 -08:00