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 16, 09:30 UTC
[Docs] Update Granite 3.0 models in supported models table (#9930)
Signed-off-by: Nick Hill <nhill@redhat.com> Signed-off-by: Nick Hill <nickhill@us.ibm.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Nick Hill committed
Nov 2, 2024 at 09:02 UTC
eed92f12fc829ff074e7341283cb1677b7e65aa2
1 file changed
+4
-4
docs/source/models/supported_models.rst
+4
-4
@@ -160,13 +160,13 @@ Text Generation
160
-
161
- ✅︎
162
* - :code:`GraniteForCausalLM`
163
- - PowerLM
164
- - :code:`ibm/PowerLM-3b` etc.
163
+ - Granite 3.0, PowerLM
164
+ - :code:`ibm-granite/granite-3.0-2b-base`, :code:`ibm-granite/granite-3.0-8b-instruct`, :code:`ibm/PowerLM-3b`, etc.
165
- ✅︎
166
- ✅︎
167
* - :code:`GraniteMoeForCausalLM`
168
- - PowerMoE
169
- - :code:`ibm/PowerMoE-3b` etc.
168
+ - Granite 3.0 MoE, PowerMoE
169
+ - :code:`ibm-granite/granite-3.0-1b-a400m-base`, :code:`ibm-granite/granite-3.0-3b-a800m-instruct`, :code:`ibm/PowerMoE-3b`, etc.
170
- ✅︎
171
- ✅︎
172
* - :code:`InternLMForCausalLM`