3183 Commits

Author SHA1 Message Date
Woosuk Kwon
f0d4e14557
Add fused top-K softmax kernel for MoE (#2769) 2024-02-05 17:38:02 -08:00
Kunshang Ji
96b6f475dd
Remove hardcoded device="cuda" to support more devices (#2503)
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2024-02-01 15:46:39 -08:00
Pernekhan Utemuratov
c410f5d020
Use revision when downloading the quantization config file (#2697)
Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
2024-02-01 15:41:58 -08:00
Fengzhe Zhou
cd9e60c76c
Add Internlm2 (#2666) 2024-02-01 09:27:40 -08:00
Philipp Moritz
d0d93b92b1
Add unit test for Mixtral MoE layer (#2677) 2024-01-31 14:34:17 -08:00
Woosuk Kwon
3dad944485
Add quantized mixtral support (#2673) 2024-01-30 16:34:10 -08:00
Woosuk Kwon
105a40f53a
[Minor] Fix false warning when TP=1 (#2674) 2024-01-30 14:39:40 -08:00
Philipp Moritz
bbe9bd9684
[Minor] Fix a small typo (#2672) 2024-01-30 13:40:37 -08:00
Philipp Moritz
ab40644669
Fused MOE for Mixtral (#2542)
Co-authored-by: chen shen <scv119@gmail.com>
2024-01-29 22:43:37 -08:00
wangding zeng
5d60def02c
DeepseekMoE support with Fused MoE kernel (#2453)
Co-authored-by: roy <jasonailu87@gmail.com>
2024-01-29 21:19:48 -08:00
zhaoyang-star
9090bf02e7
Support FP8-E5M2 KV Cache (#2279)
Co-authored-by: zhaoyang <zhao.yang16@zte.com.cn>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-28 16:43:54 -08:00
Hanzhi Zhou
380170038e
Implement custom all reduce kernels (#2192) 2024-01-27 12:46:35 -08:00
Casper
beb89f68b4
AWQ: Up to 2.66x higher throughput (#2566) 2024-01-26 23:53:17 -08:00
dakotamahan-stability
3a0e1fc070
Support for Stable LM 2 (#2598)
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-26 12:45:19 -08:00
Junyang Lin
2832e7b9f9
fix names and license for Qwen2 (#2589) 2024-01-24 22:37:51 -08:00
Antoni Baum
9b945daaf1
[Experimental] Add multi-LoRA support (#1804)
Co-authored-by: Chen Shen <scv119@gmail.com>
Co-authored-by: Shreyas Krishnaswamy <shrekris@anyscale.com>
Co-authored-by: Avnish Narayan <avnish@anyscale.com>
2024-01-23 15:26:37 -08:00
Junyang Lin
94b5edeb53
Add qwen2 (#2495) 2024-01-22 14:34:21 -08:00
Cade Daniel
18bfcdd05c
[Speculative decoding 2/9] Multi-step worker for draft model (#2424) 2024-01-21 16:31:47 -08:00
Junda Chen
5b23c3f26f
Add group as an argument in broadcast ops (#2522) 2024-01-20 16:00:26 -08:00
Roy
91a61da9b1
[Bugfix] fix load local safetensors model (#2512) 2024-01-19 16:26:16 -08:00
Zhuohan Li
ef9b636e2d
Simplify broadcast logic for control messages (#2501) 2024-01-19 11:23:30 -08:00
Simon Mo
dd7e8f5f64
refactor complemention api for readability (#2499) 2024-01-18 16:45:14 -08:00
Nikola Borisov
7e1081139d
Don't download both safetensor and bin files. (#2480) 2024-01-18 11:05:53 -08:00
YingchaoX
8a25d3a71a
fix stablelm.py tensor-parallel-size bug (#2482) 2024-01-18 09:39:46 -08:00
shiyi.c_98
d10f8e1d43
[Experimental] Prefix Caching Support (#1669)
Co-authored-by: DouHappy <2278958187@qq.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>
2024-01-17 16:32:10 -08:00
Hyunsung Lee
e1957c6ebd
Add StableLM3B model (#2372) 2024-01-16 20:32:40 -08:00
Chenhui Zhang
f780504d12
fix weigit loading for GQA with TP (#2379) 2024-01-15 15:43:59 -08:00
陈序
218dc2ccda
Aligning top_p and top_k Sampling (#1885)
* Align top_p and top_k with huggingface

* remove _get_prompt_and_output_tokens

* rename _apply_top_p_top_k

* compare top_p top_k with hf

* fix test errors
2024-01-12 22:51:03 +01:00
Gary Hui
7878958c0d
Address Phi modeling update 2 (#2428) 2024-01-12 12:16:49 -08:00
Woosuk Kwon
50376faa7b
Rename phi_1_5 -> phi (#2385) 2024-01-11 16:23:43 -08:00
Cade Daniel
79d64c4954
[Speculative decoding 1/9] Optimized rejection sampler (#2336) 2024-01-09 15:38:41 -08:00
Woosuk Kwon
28c3f12104
[Minor] Remove unused code in attention (#2384) 2024-01-08 13:13:08 -08:00
Zhuohan Li
fd4ea8ef5c
Use NCCL instead of ray for control-plane communication to remove serialization overhead (#2221) 2024-01-03 11:30:22 -08:00
Roy
9140561059
[Minor] Fix typo and remove unused code (#2305) 2024-01-02 19:23:15 -08:00
Jong-hun Shin
4934d49274
Support GPT-NeoX Models without attention biases (#2301) 2023-12-30 11:42:04 -05:00
Antoni Baum
bd29cf3d3a
Remove Sampler copy stream (#2209) 2023-12-20 00:04:33 -08:00
Woosuk Kwon
ba4f826738
[BugFix] Fix weight loading for Mixtral with TP (#2208) 2023-12-19 16:16:11 -08:00
avideci
de60a3fb93
Added DeciLM-7b and DeciLM-7b-instruct (#2062) 2023-12-19 02:29:33 -08:00
Woosuk Kwon
2c9b638065
[Minor] Fix a typo in .pt weight support (#2160) 2023-12-17 10:12:44 -08:00
Antoni Baum
a7347d9a6d
Make sampler less blocking (#1889) 2023-12-17 23:03:49 +08:00
Woosuk Kwon
c3372e87be
Remove dependency on CuPy (#2152) 2023-12-17 01:49:07 -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
CHU Tianxiang
0fbfc4b81b
Add GPTQ support (#916) 2023-12-15 03:04:22 -08:00
Antoni Baum
21d93c140d
Optimize Mixtral with expert parallelism (#2090) 2023-12-13 23:55:07 -08:00
Woosuk Kwon
518369d78c
Implement lazy model loader (#2044) 2023-12-12 22:21:45 -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
cb3f30c600
Upgrade transformers version to 4.36.0 (#2046) 2023-12-11 18:39:14 -08:00
Woosuk Kwon
31d2ab4aff
Remove python 3.10 requirement (#2040) 2023-12-11 12:26:42 -08:00
Woosuk Kwon
6120e5aaea
Fix import error msg for megablocks (#2038) 2023-12-11 11:40:56 -08:00