text-generation-inference
bitsandbytes
text-generation-inference | bitsandbytes | |
---|---|---|
29 | 61 | |
7,881 | 5,447 | |
6.2% | - | |
9.6 | 9.4 | |
6 days ago | 2 days ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
text-generation-inference
- FLaNK AI-April 22, 2024
-
Zephyr 141B, a Mixtral 8x22B fine-tune, is now available in Hugging Chat
I wanted to write that TGI inference engine is not Open Source anymore, but they have reverted the license back to Apache 2.0 for the new version TGI v2.0: https://github.com/huggingface/text-generation-inference/rel...
Good news!
- Hugging Face reverts the license back to Apache 2.0
- HuggingFace text-generation-inference is reverting to Apache 2.0 License
- FLaNK Stack 05 Feb 2024
- Is there any open source app to load a model and expose API like OpenAI?
-
AI Code assistant for about 50-70 users
Setting up a server for multiple users is very different from setting up LLM for yourself. A safe bet would be to just use TGI, which supports continuous batching and is very easy to run via Docker on your server. https://github.com/huggingface/text-generation-inference
-
LocalPilot: Open-source GitHub Copilot on your MacBook
Okay, I actually got local co-pilot set up. You will need these 4 things.
1) CodeLlama 13B or another FIM model https://huggingface.co/codellama/CodeLlama-13b-hf. You want "Fill in Middle" models because you're looking at context on both sides of your cursor.
2) HuggingFace llm-ls https://github.com/huggingface/llm-ls A large language mode Language Server (is this making sense yet)
3) HuggingFace inference framework. https://github.com/huggingface/text-generation-inference At least when I tested you couldn't use something like llama.cpp or exllama with the llm-ls, so you need to break out the heavy duty badboy HuggingFace inference server. Just config and run. Now config and run llm-ls.
4) Okay, I mean you need an editor. I just tried nvim, and this was a few weeks ago, so there may be better support. My expereicen was that is was full honest to god copilot. The CodeLlama models are known to be quite good for its size. The FIM part is great. Boilerplace works so much easier with the surrounding context. I'd like to see more models released that can work this way.
-
Mistral 7B Paper on ArXiv
A simple microservice would be https://github.com/huggingface/text-generation-inference .
Works flawlessly in Docker on my Windows machine, which is extremely shocking.
-
best way to serve llama V2 (llama.cpp VS triton VS HF text generation inference)
I am wondering what is the best / most cost-efficient way to serve llama V2. - llama.cpp (is it production ready or just for playing around?) ? - Triton inference server ? - HF text generation inference ?
bitsandbytes
-
French AI startup Mistral secures €2B valuation
No. Without the inference code, the best we can have are guesses on its implementation, so the benchmark figures we can get could be quite wrong. It does seem better than Llama2-70B in my tests, which rely on the work done by Dmytro Dzhulgakov[0] and DiscoResearch[1].
But the point of releasing on bittorrent is to see the effervescence in hobbyist research and early attempts at MoE quantization, which are already ongoing[2]. They are benefitting from the community.
[0]: https://github.com/dzhulgakov/llama-mistral
[1]: https://huggingface.co/DiscoResearch/mixtral-7b-8expert
[2]: https://github.com/TimDettmers/bitsandbytes/tree/sparse_moe
-
Lora training with Kohya issue
CUDA SETUP: To manually override the PyTorch CUDA version please see:https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
- FLaNK Stack Weekly for 30 Oct 2023
-
A comprehensive guide to running Llama 2 locally
While on the surface, a 192GB Mac Studio seems like a great deal (it's not much more than a 48GB A6000!), there are several reasons why this might not be a good idea:
* I assume most people have never used llama.cpp Metal w/ large models. It will drop to CPU speeds whenever the context window is full: https://github.com/ggerganov/llama.cpp/issues/1730#issuecomm... - while sure this might be fixed in the future, it's been an issue since Metal support was added, and is a significant problem if you are actually trying to actually use it for inferencing. With 192GB of memory, you could probably run larger models w/o quantization, but I've never seen anyone post benchmarks of their experiences. Note that at that point, the limited memory bandwidth will be a big factor.
* If you are planning on using Apple Silicon for ML/training, I'd also be wary. There are multi-year long open bugs in PyTorch[1], and most major LLM libs like deepspeed, bitsandbytes, etc don't have Apple Silicon support[2][3].
You can see similar patterns w/ Stable Diffusion support [4][5] - support lagging by months, lots of problems and poor performance with inference, much less fine tuning. You can apply this to basically any ML application you want (srt, tts, video, etc)
Macs are fine to poke around with, but if you actually plan to do more than run a small LLM and say "neat", especially for a business, recommending a Mac for anyone getting started w/ ML workloads is a bad take. (In general, for anyone getting started, unless you're just burning budget, renting cloud GPU is going to be the best cost/perf, although on-prem/local obviously has other advantages.)
[1] https://github.com/pytorch/pytorch/issues?q=is%3Aissue+is%3A...
[2] https://github.com/microsoft/DeepSpeed/issues/1580
[3] https://github.com/TimDettmers/bitsandbytes/issues/485
[4] https://github.com/AUTOMATIC1111/stable-diffusion-webui/disc...
[5] https://forums.macrumors.com/threads/ai-generated-art-stable...
-
Bit inference 4.2x faster than 16 bit
Release notes: https://github.com/TimDettmers/bitsandbytes/releases/tag/0.4...
-
Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0']
Welcome to bitsandbytes. For bug reports, please run python -m bitsandbytes and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues ================================================================================ bin /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cpu.so /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cpu.so: undefined symbol: cadam32bit_grad_fp32 CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths... ERROR: /usr/bin/python3: undefined symbol: cudaRuntimeGetVersion CUDA SETUP: libcudart.so path is None CUDA SETUP: Is seems that your cuda installation is not in your path. See https://github.com/TimDettmers/bitsandbytes/issues/85 for more information. CUDA SETUP: CUDA version lower than 11 are currently not supported for LLM.int8(). You will be only to use 8-bit optimizers and quantization routines!! CUDA SETUP: Highest compute capability among GPUs detected: 7.5 CUDA SETUP: Detected CUDA version 00 CUDA SETUP: Loading binary /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cpu.so... /usr/local/lib/python3.10/dist-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable. warn("The installed version of bitsandbytes was compiled without GPU support. " /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /usr/lib64-nvidia did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths... warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')} warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('http'), PosixPath('//172.28.0.1'), PosixPath('8013')} warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-1b6gsytv7z9le --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true'), PosixPath('--logtostderr --listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https')} warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')} warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')} warn(msg) /usr/local/lib/python3.10/dist-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!
-
Having trouble using the multimodal tools.
RuntimeError: CUDA Setup failed despite GPU being available. Inspect the CUDA SETUP outputs above to fix your environment! If you cannot find any issues and suspect a bug, please open an issue with detals about your environment: https://github.com/TimDettmers/bitsandbytes/issues
- [TextGen WebUI] Service terminated error? (Screenshots in post)
- Considering getting a Jetson AGX Orin.. anyone have experience with it?
-
How to disable the `bitsandbytes` intro message:
===================================BUG REPORT=================================== Welcome to bitsandbytes. For bug reports, please run python -m bitsandbytes and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues ================================================================================ bin /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda121.so CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths... CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so CUDA SETUP: Highest compute capability among GPUs detected: 8.9 CUDA SETUP: Detected CUDA version 121 CUDA SETUP: Loading binary /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda121.so...
What are some alternatives?
llama-cpp-python - Python bindings for llama.cpp
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
accelerate - 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
exllama - A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
Dreambooth-Stable-Diffusion-cpu - Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion
FlexGen - Running large language models on a single GPU for throughput-oriented scenarios.
llama.cpp - LLM inference in C/C++
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM