A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 06:45 UTC
[Fix] Update Supported Models List (#1690)
Zhuohan Li committed
Nov 16, 2023 at 14:47 UTC
415d1095278d896135728a54b4307dde3bc83243
2 files changed
+11
README.md
+2
@@ -49,6 +49,7 @@ vLLM seamlessly supports many Hugging Face models, including the following archi
49
- Aquila & Aquila2 (`BAAI/AquilaChat2-7B`, `BAAI/AquilaChat2-34B`, `BAAI/Aquila-7B`, `BAAI/AquilaChat-7B`, etc.)
50
- Baichuan (`baichuan-inc/Baichuan-7B`, `baichuan-inc/Baichuan-13B-Chat`, etc.)
51
- BLOOM (`bigscience/bloom`, `bigscience/bloomz`, etc.)
52
+- ChatGLM (`THUDM/chatglm2-6b`, `THUDM/chatglm3-6b`, etc.)
53
- Falcon (`tiiuae/falcon-7b`, `tiiuae/falcon-40b`, `tiiuae/falcon-rw-7b`, etc.)
54
- GPT-2 (`gpt2`, `gpt2-xl`, etc.)
55
- GPT BigCode (`bigcode/starcoder`, `bigcode/gpt_bigcode-santacoder`, etc.)
@@ -61,6 +62,7 @@ vLLM seamlessly supports many Hugging Face models, including the following archi
62
- OPT (`facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc.)
63
- Phi-1.5 (`microsoft/phi-1_5`, etc.)
64
- Qwen (`Qwen/Qwen-7B`, `Qwen/Qwen-7B-Chat`, etc.)
65
+- Yi (`01-ai/Yi-6B`, `01-ai/Yi-34B`, etc.)
66
67
Install vLLM with pip or [from source](https://vllm.readthedocs.io/en/latest/getting_started/installation.html#build-from-source):
68
docs/source/models/supported_models.rst
+9
@@ -20,6 +20,9 @@ Alongside each architecture, we include some popular models that use it.
20
* - :code:`BaiChuanForCausalLM`
21
- Baichuan
22
- :code:`baichuan-inc/Baichuan-7B`, :code:`baichuan-inc/Baichuan-13B-Chat`, etc.
23
+ * - :code:`ChatGLMModel`
24
+ - ChatGLM
25
+ - :code:`THUDM/chatglm2-6b`, :code:`THUDM/chatglm3-6b`, etc.
26
* - :code:`BloomForCausalLM`
27
- BLOOM, BLOOMZ, BLOOMChat
28
- :code:`bigscience/bloom`, :code:`bigscience/bloomz`, etc.
@@ -53,9 +56,15 @@ Alongside each architecture, we include some popular models that use it.
56
* - :code:`OPTForCausalLM`
57
- OPT, OPT-IML
58
- :code:`facebook/opt-66b`, :code:`facebook/opt-iml-max-30b`, etc.
59
+ * - :code:`PhiForCausalLM`
60
+ - Phi-1.5
61
+ - :code:`microsoft/phi-1_5`, etc.
62
* - :code:`QWenLMHeadModel`
63
- Qwen
64
- :code:`Qwen/Qwen-7B`, :code:`Qwen/Qwen-7B-Chat`, etc.
65
+ * - :code:`YiForCausalLM`
66
+ - Yi
67
+ - :code:`01-ai/Yi-6B`, :code:`01-ai/Yi-34B`, etc.
68
69
If your model uses one of the above model architectures, you can seamlessly run your model with vLLM.
70
Otherwise, please refer to :ref:`Adding a New Model <adding_a_new_model>` for instructions on how to implement support for your model.