vllm
mlc-llm
vllm | mlc-llm | |
---|---|---|
31 | 89 | |
19,344 | 17,150 | |
12.6% | 4.3% | |
9.9 | 9.9 | |
2 days ago | 3 days ago | |
Python | Python | |
Apache License 2.0 | 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.
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
- Mixtral 8x7B Support
mlc-llm
- FLaNK 04 March 2024
-
Ai on a android phone?
This one uses gpu, it doesn't support Mistral yet: https://github.com/mlc-ai/mlc-llm
-
MLC vs llama.cpp
I have tried running mistral 7B with MLC on my m1 metal. And it kept crushing (git issue with description). Memory inefficiency problems.
-
[Project] Scaling LLama2 70B with Multi NVIDIA and AMD GPUs under 3k budget
Project: https://github.com/mlc-ai/mlc-llm
- Scaling LLama2-70B with Multi Nvidia/AMD GPU
-
AMD May Get Across the CUDA Moat
For LLM inference, a shoutout to MLC LLM, which runs LLM models on basically any API that's widely available: https://github.com/mlc-ai/mlc-llm
-
ROCm Is AMD's #1 Priority, Executive Says
One of your problems might be that gfx1032 is not supported by AMD's ROCm packages, which has a laughably short list of supported hardware: https://rocm.docs.amd.com/en/latest/release/gpu_os_support.h...
The normal workaround is to assign the closest architecture, eg gfx1030, so `HSA_OVERRIDE_GFX_VERSION=10.3.0` might help
Also, it looks like some of your tested projects are OpenCL? For me, I do something like: `yay -S rocm-hip-sdk rocm-ml-sdk rocm-opencl-sdk` to cover all the bases.
My recent interest has been LLMs and this is my general step by step for those (llama.cpp, exllama) for those interested: https://llm-tracker.info/books/howto-guides/page/amd-gpus
I didn't port the docs back in, but also here's a step-by-step w/ my adventures getting TVM/MLC working w/ an APU: https://github.com/mlc-ai/mlc-llm/issues/787
From my experience, ROCm is improving, but there's a good reason that Nvidia has 90% market share even at big price premiums.
-
Show HN: Ollama for Linux – Run LLMs on Linux with GPU Acceleration
Maybe they're talking about https://github.com/mlc-ai/mlc-llm which is used for web-llm (https://github.com/mlc-ai/web-llm)? Seems to be using TVM.
-
Show HN: Fine-tune your own Llama 2 to replace GPT-3.5/4
you already have TVM for the cross platform stuff
see https://tvm.apache.org/docs/how_to/deploy/android.html
or https://octoml.ai/blog/using-swift-and-apache-tvm-to-develop...
or https://github.com/mlc-ai/mlc-llm
- Ask HN: Are you training and running custom LLMs and how are you doing it?
What are some alternatives?
TensorRT - NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
llama.cpp - LLM inference in C/C++
CTranslate2 - Fast inference engine for Transformer models
ggml - Tensor library for machine learning
lmdeploy - LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
tvm - Open deep learning compiler stack for cpu, gpu and specialized accelerators
Llama-2-Onnx
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
tritony - Tiny configuration for Triton Inference Server
llama-cpp-python - Python bindings for llama.cpp
faster-whisper - Faster Whisper transcription with CTranslate2
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.