-
When attempting to pip install mamba-ssm
I receive this error:
(mistEnv) C:\Users\gavin\mistRL>pip install mamba_ssm
Collecting mamba_ssm
Using cached mamba_ssm-2.2.2.tar.gz (85 kB)
Insta…
-
### Willingness to contribute
No. I cannot contribute this feature at this time.
### Proposal Summary
The 2.12.2 release added support for the `predict_stream` method for custom Python models. Whil…
-
Hi, I recently read the paper llumnix. I really like the idea. It is simple and working. I would like to ask whether llumnix can support the newest vLLM or not. If not, is there any doc which lists th…
-
RTX 4090 24G,
Qwen-7B-Chat
loads OK:
```
model_config = ModelConfig(lora_infos={
"lora_1": conf['lora_1'],
"lora_2": conf['lora_2'],
})
model = ModelFactory.from_huggingface(conf['b…
-
Hi team
Do you have any examples or know of any videos of people showing this?
I literally can't find a thing - but it sounds really good for RAG.
However, as you can imagine, searching web or Yo…
-
First of all, thank you for a great job! I ran into a few issues while following the tutorial to reproduce:
I first follow [tutorial](https://github.com/FudanDISC/ReForm-Eval#create-your-own-model-…
-
### Description
TAdd a new flag, `-m`, which allows users to specify their own commit message as a basis. OpenCommit will then enhance and improve this user-provided message using the LLM.
### Sugge…
-
LiteLLM already support Gemini so it's probably already doable. Would be nice to support it OOTB as Gemini has a large context window
-
- Description:
- The autoregressive decoding mode of LLM determines that LLM can only be decoded serially, which limits its inference speed. Speculative decoding technique can be used to decode L…
-
I saw you post this repo looking for contributors but you didn't really say any topic you'd like help with. To be completely honest I don't know anything about audio processing, but I have been tinker…