talk
vllm
![SurveyJS Logo](https://cdn-b.libhunt.com/images/promo-campaign-images/000/000/030/main.png?1674177924)
talk | vllm | |
---|---|---|
3 | 32 | |
564 | 21,104 | |
- | 10.5% | |
8.1 | 9.9 | |
8 months ago | about 3 hours ago | |
TypeScript | Python | |
- | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
talk
-
ChatGPT can now see, hear, and speak – openai.com
Also curious to hear about your setup. Using whisper too? When I was experimenting with it there was still a lot of annoyance about hallucinations and I was hard coding some "if last phrase is 'thanks for watching', ignore last phrase"
I was just googling a bit to see what's out there now for whisper/llama combos and came across this: https://github.com/yacineMTB/talk
There's a demo linked on the github page that seems relatively fast at responding conversationally, but still maybe 1-2 seconds at times. Impressive it's entirely offline.
- Is anyone doing always-on voice to text with a local llama at home?
-
Giving LLM’s a <Backspace> Token
Here’s a project attempting to do just this!
https://github.com/yacineMTB/talk
vllm
-
Best LLM Inference Engines and Servers to Deploy LLMs in Production
GitHub repository: https://github.com/vllm-project/vllm
-
AI leaderboards are no longer useful. It's time to switch to Pareto curves
I guess the root cause of my claim is that OpenAI won't tell us whether or not GPT-3.5 is an MoE model, and I assumed it wasn't. Since GPT-3.5 is clearly nondeterministic at temp=0, I believed the nondeterminism was due to FPU stuff, and this effect was amplified with GPT-4's MoE. But if GPT-3.5 is also MoE then that's just wrong.
What makes this especially tricky is that small models are truly 100% deterministic at temp=0 because the relative likelihoods are too coarse for FPU issues to be a factor. I had thought 3.5 was big enough that some of its token probabilities were too fine-grained for the FPU. But that's probably wrong.
On the other hand, it's not just GPT, there are currently floating-point difficulties in vllm which significantly affect the determinism of any model run on it: https://github.com/vllm-project/vllm/issues/966 Note that a suggested fix is upcasting to float32. So it's possible that GPT-3.5 is using an especially low-precision float and introducing nondeterminism by saving money on compute costs.
Sadly I do not have the money[1] to actually run a test to falsify any of this. It seems like this would be a good little research project.
[1] Or the time, or the motivation :) But this stuff is expensive.
-
Mistral AI Launches New 8x22B Moe Model
The easiest is to use vllm (https://github.com/vllm-project/vllm) to run it on a Couple of A100's, and you can benchmark this using this library (https://github.com/EleutherAI/lm-evaluation-harness)
- FLaNK AI for 11 March 2024
-
Show HN: We got fine-tuning Mistral-7B to not suck
Great question! scheduling workloads onto GPUs in a way where VRAM is being utilised efficiently was quite the challenge.
What we found was the IO latency for loading model weights into VRAM will kill responsiveness if you don't "re-use" sessions (i.e. where the model weights remain loaded and you run multiple inference sessions over the same loaded weights).
Obviously projects like https://github.com/vllm-project/vllm exist but we needed to build out a scheduler that can run a fleet of GPUs for a matrix of text/image vs inference/finetune sessions.
disclaimer: I work on Helix
-
Mistral CEO confirms 'leak' of new open source AI model nearing GPT4 performance
FYI, vLLM also just added experiment multi-lora support: https://github.com/vllm-project/vllm/releases/tag/v0.3.0
Also check out the new prefix caching, I see huge potential for batch processing purposes there!
- VLLM Sacrifices Accuracy for Speed
- Easy, fast, and cheap LLM serving for everyone
- vllm
- Mixtral Expert Parallelism
What are some alternatives?
llama_farm - Use local llama LLM or openai to chat, discuss/summarize your documents, youtube videos, and so on.
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
willow - Open source, local, and self-hosted Amazon Echo/Google Home competitive Voice Assistant alternative
CTranslate2 - Fast inference engine for Transformer models
chatcraft.org - Developer-oriented ChatGPT clone
lmdeploy - LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
awesome-talking-head-generation
Llama-2-Onnx
whisper-live-transcription - Live-Transcription (STT) with Whisper PoC
tritony - Tiny configuration for Triton Inference Server
nerd-dictation - Simple, hackable offline speech to text - using the VOSK-API.
faster-whisper - Faster Whisper transcription with CTranslate2
![SurveyJS Logo](https://cdn-b.libhunt.com/images/promo-campaign-images/000/000/030/main.png?1674177924)