Cyrus Leung
7025b11d94
[Bugfix] Fix weight loading for Chameleon when TP>1 ( #7410 )
2024-08-13 05:33:41 +00:00
ee93f4f92a
[CORE] Quantized lm-head Framework ( #4442 )
...
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com >
Co-authored-by: ZX <zx@lbx.dev >
2024-07-02 22:25:17 +00:00
Murali Andoorveedu
c5832d2ae9
[Core] Pipeline Parallel Support ( #4412 )
...
Signed-off-by: Muralidhar Andoorveedu <muralidhar.andoorveedu@centml.ai >
2024-07-02 10:58:08 -07:00
Cyrus Leung
98cf2ed678
[Model][Bugfix] Implicit model flags and reenable Phi-3-Vision ( #5896 )
2024-06-27 09:08:10 -07:00
Cyrus Leung
96354d6a29
[Model] Add base class for LoRA-supported models ( #5018 )
2024-06-27 16:03:04 +08:00
Cody Yu
a3a73ab069
[Misc] Load FP8 kv-cache scaling factors from checkpoints ( #4893 )
...
The 2nd PR for #4532 .
This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
2024-05-22 13:28:20 -07:00
SangBin Cho
2e9a2227ec
[Lora] Support long context lora ( #4787 )
...
Currently we need to call rotary embedding kernel for each LoRA, which makes it hard to serve multiple long context length LoRA. Add batched rotary embedding kernel and pipe it through.
It replaces the rotary embedding layer to the one that is aware of multiple cos-sin-cache per scaling factors.
Follow up of https://github.com/vllm-project/vllm/pull/3095/files
2024-05-18 16:05:23 +09:00
Woosuk Kwon
0fca3cdcf2
[Misc] Enhance attention selector ( #4751 )
2024-05-13 10:47:25 -07:00
Cody Yu
a62aaf1df5
[Misc][Refactor] Generalize linear_method to be quant_method ( #4373 )
2024-04-26 16:41:14 -04:00
Antoni Baum
69e1d2fb69
[Core] Refactor model loading code ( #4097 )
2024-04-16 11:34:39 -07:00
youkaichao
63e7176f26
[Core][Refactor] move parallel_utils into vllm/distributed ( #3950 )
...
[WIP][Core][Refactor] move vllm/model_executor/parallel_utils into vllm/distributed and vllm/device_communicators (#3950 )
2024-04-10 15:33:30 -07:00
Jee Li and Antoni Baum
8af890a865
Enable more models to inference based on LoRA ( #3382 )
...
Co-authored-by: Antoni Baum <antoni.baum@protonmail.com >
2024-03-25 18:09:31 -07:00
SangBin Cho
01bfb22b41
[CI] Try introducing isort. ( #3495 )
2024-03-25 07:59:47 -07:00
Woosuk Kwon
925f3332ca
[Core] Refactor Attention Take 2 ( #3462 )
2024-03-25 04:39:33 +00:00
Roy
f1c0fc3919
Migrate logits computation and gather to model_runner ( #3233 )
2024-03-20 23:25:01 +00:00
Woosuk Kwon
2daf23ab0c
Separate attention backends ( #3005 )
2024-03-07 01:45:50 -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
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
CHU Tianxiang
0fbfc4b81b
Add GPTQ support ( #916 )
2023-12-15 03:04:22 -08:00
Woosuk Kwon
27feead2f8
Refactor Worker & InputMetadata ( #1843 )
2023-11-29 22:16:37 -08:00
Woosuk Kwon
a9e4574261
Refactor Attention ( #1840 )
2023-11-29 15:37:31 -08:00
Woosuk Kwon
a7b3e33078
[Fix] Fix RoPE in ChatGLM-32K ( #1841 )
2023-11-29 13:01:19 -08:00
Woosuk Kwon
7c600440f7
Fix model docstrings ( #1764 )
2023-11-23 23:04:44 -08:00
Simon Mo
5ffc0d13a2
Migrate linter from pylint to ruff ( #1665 )
2023-11-20 11:58:01 -08:00
Zhuohan Li
7076fa1c9f
TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models ( #1622 )
...
Refactor the tensor parallelism, quantization, and weight-loading codes.
Summary of the new features enabled by this PR:
- **All models** are able to be quantized with AWQ and SqueezeLLM, and [soon GPTQ](https://github.com/vllm-project/vllm/pull/1580 ).
- Model loading code became much simpler.
- Support model parallelism for all MQA/GQA models when the number of key/value heads is smaller than the tensor parallel size.
2023-11-15 22:50:41 -08:00
GoHomeToMacDonal
1a2bbc9301
ChatGLM Support ( #1261 )
2023-11-06 16:09:33 -08:00
Cyrus Leung