Aphrodite-engine

Latest version: v0.6.3.post1

Safety actively analyzes 681866 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 2 of 5

0.6.0.post1

What's Changed
* feat: add siglip encoder for llava family by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/626
* readme: fix model name typo by Trapper4888 in https://github.com/PygmalionAI/aphrodite-engine/pull/627
* feat: multi-image input for minicpmv by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/628
* feat: Add support for GPU device selection in SpecDecodeBaseSampler by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/629
* feat: per-tensor token epilogue kernels by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/630
* chore: optimize evictor v2 performance by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/631
* feat: initial encoder-decoder support with BART model by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/633
* fix: default api port and attention selector by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/634
* fix: clean up incorrect log in worker by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/636
* bump to v0.6.0.post1 by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/635

New Contributors
* Trapper4888 made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/627

**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.6.0...v0.6.0.post1

0.6.0

New Contributors
* matthusby made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/538

**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.5.3...v0.6.0

0.5.3

What's Changed
A new release, one that took too long again. We have some cool new features, however.

- **ExllamaV2 tensor parallel**: You can now run ExllamaV2 quantized models on multiple GPUs. This should be the fastest multi-gpu experience with exllamav2 models.
- **Support for Command-R+**
- **Support for DBRX**
- **Support for Llama-3**
- **Support for Qwen 2 MoE**
- **`min_tokens` sampling param**: You can now set a minimum amount of tokens to generate.
- **Fused MoE for AWQ and GPTQ quants**: AWQ and GPTQ kernels have been updated with optimized fused MoE code. They should be significantly faster now.
- **CMake build system**: Slightly faster, much cleaner builds.
- **CPU support**: You can now run aphrodite on CPU only systems! Needs an AVX512-compatible CPU for now.
- **Speculative Decoding**: Speculative Decoding is finally here! You can either use a draft model, or use prompt lookup decoding with an ngram model (built-in).
- **Chunked Prefill**: Before this, Aphrodite would process prompts in chunks equal to the model's context length. Now, you can enable this option (via `--enable-chunked-prefill`) to process in chunks of 768 by default, massively increasing the amount of context you can fit. Does not currently work with context shift or FP8 KV cache.
- **Context Shift reworked**: Context shift finally works now. Enable it with `--context-shift` and Aphrodite will cache processed prompts and re-use them.
- **FP8 E4M3 KV Cache**: This is for ROCm only. Support will be extended to NVIDIA soon. E4M3 has higher quality compared to E5M2, but doesn't lead to any throughput increase.
- **Auto-truncation in API**: The API server can now optionally left-truncate your prompts. Simply pass `truncate_prompt_tokens=1024` to truncate any prompt larger than 1024 tokens.
- **Support for Llava vision models**: Currently 1.5 is supported. With the next release, we should have 1.6 along with a proper GPT4-V compatible API.
- **LM Format Enforcer**: You can now use LMFE for guided generations.
- **EETQ Quantization**: EETQ support has been added - a SOTA 8bit quantization method.
- **Arbitrary GGUF model support**: We were limited to only Llama models for GGUF, now any GGUF is supported. You will need to convert the model beforehand for them, however.
- **Aphrodite CLI app**: You no longer have to type `python -m aphrodite...`. Simply type `aphrodite run meta-llama/Meta-Llama-3-8B` to get started. Pass extra flags as normal.
- **Sharded GGUF support**: You can now load sharded GGUF models. Pre-conversion needed.
- **NVIDIA P100/GP100 support**: Support has been restored.

Thanks to all the new contributors!

**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.5.2...v0.5.3

0.5.2

What's Changed

A few fixes and new additions:

- **Support for CohereAI's command-r model**: Currently, GGUF is unsupported. You can load the base model with `--load-in-4bit` or `--load-in-smooth` if you have an RTX 20xx series (or sm_75).
- Fix an issue where some GPU blocks were missing. This should give a significant boost to how much context you can use.
- Fix logprobs when -inf with some models.


**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.5.1...v0.5.2

0.5.1

What's Changed
* feat(openai): Apply chat template for GGUF loader by drummerv in https://github.com/PygmalionAI/aphrodite-engine/pull/312
* Calculate total memory usage. by sgsdxzy in https://github.com/PygmalionAI/aphrodite-engine/pull/316
* chore: add new iMatrix quants by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/320
* fix: optimize AQLM dequantization by AlpinDale in https://github.com/PygmalionAI/aphrodite-engine/pull/325

New Contributors
* drummerv made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/312

**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.5.0...v0.5.1

0.5.0

Aphrodite Engine, Release v0.5.0: It's Quantin' Time Edition

It's been over a month since our last release. Below is re-written using Opus from my crude hand-written release notes.

New Features

- **Exllamav2 Quantization**: Exllamav2 quantization has been added, although it's currently limited to a single GPU due to kernel constraints.

- **On-the-Fly Quantization**: With the help of `bitsandbytes` and `smoothquant+`, we now support on-the-fly quantization of FP16 models. Use `--load-in-4bit` for lightning-fast 4-bit quantization with `smoothquant+`, `--load-in-smooth` for 8-bit quantization using `smoothquant+`, and `--load-in-8bit` for 8-bit quantization using the `bitsandbytes` library (note: this option is quite slow). `--load-in-4bit` needs Ampere GPUs and above, the other two need Turing and above.

- **Marlin Quantization**: Marlin quantization support has arrived, promising improved speeds at high batch sizes. Convert your GPTQ models to Marlin, but keep in mind that they must be 4-bit, with a group_size of -1 or 128, and act_order set to False.

- **AQLM Quantization**: We now support the state-of-the-art 2-bit quantization scheme, AQLM. Please note that both quantization and inference are extremely slow with this method. Quantizing llama-2 70b on 8x A100s reportedly takes 12 days, and on a single 3090 it takes 70 seconds to reach the prompt processing phase. Use this option with caution, as the wait process may cause the engine to timeout (set to 60 seconds).

- **INT8 KV Cache Quantization**: In addition to fp8_e5m2, we now support INT8 KV Cache. Unlike FP8, it doesn't speed up the throughput (it stays the same), but should offer higher quality, due to the calibration process. Uses the `smoothquant` algorithm for the quantization.

- **Implicit GGUF Model Conversion**: Simply point the `--model` flag to your GGUF file, and it will work out of the box. Be aware that this process requires a considerable amount of RAM to load the model, convert tensors to a PyTorch state_dict, and then load them. Plan accordingly or convert first if you're short on RAM.

- **LoRA support in the API**: The API now supports loading and inferencing LoRAs! Please refer to the wiki for detailed instructions.

- **New Model Support**: We've added support for a wide range of models, including OPT, Baichuan, Bloom, ChatGLM, Falcon, Gemma, GPT2, GPT Bigcode, InternLM2, MPT, OLMo, Qwen, Qwen2, and StableLM.

- **Fused Mixtral MoE**: Mixtral models (FP16 only) now utilize tensor parallelism with fused kernels, replacing the previous expert parallelism approach. Quantized Mixtrals still have this limitation, but we plan to address it by the next release.

- **Fused Top-K Kernels for MoE**: This improvement benefits Mixtral and DeepSeek-MoE models by accelerating the top-k operation using custom CUDA kernels instead of `torch.topk`.

- **Enhanced OpenAI Endpoint**: The OpenAI endpoint has been refactored, introducing JSON and Regex schemas, as well as a detokenization endpoint.

- **LoRA Support for Mixtral Models**: You can now use LoRA with Mixtral models.

- **Fine-Grained Seeds**: Introduce randomness to your requests with per-request seeds.

- **Context Shift**: We have a naive context shifting mechanism. While it's not as effective as we'd like, it's available for experimentation purposes. Enable it using the `--context-shift` flag.

- **Cubic Sampling**: Building upon quadratic sampling's smoothing_factor, we now support smoothing_curve.

- **Navi AMD GPU Support**: GPUs like the 7900 XTX are now supported, although still experimental and requiring significant compilation efforts due to xformers.

- **Kobold API Deprecation**: The Kobold API has been deprecated and merged into the OpenAI API. Launch the OpenAI API using the `--launch-kobold-api` flag. Please note that Kobold routes are not protected with the API key.

- **LoRA Support for Quantized Models**: We've added LoRA support for GPTQ and AWQ quantized models.

- **Logging Experience Overhaul**: We've revamped the logging experience using a custom `loguru` class, inspired by tabbyAPI's recent changes.

- **Informative Logging Metrics**: Logging has been enhanced to display model memory usage and reduce display bloat, among other improvements.

- **Ray Worker Health Check**: The engine now performs health checks on Ray workers, promptly reporting any silent failures or timeouts.

Bug Fixes

- Resolved an issue where `smoothing_factor` would break at high batch sizes.
- Fixed a bug with LoRA vocab embeddings.
- Addressed the missing CUDA suffixes in the version number (e.g., `0.5.0+cu118`). The suffix is now appended when using a CUDA version other than 12.1.
- Dynatemp has been split into min/max from range. The Kobold endpoint still accepts a range as input.
- Fixed worker initialization in WSL.
- Removed the accidental inclusion of FP8 kernels in the ROCm build process.
- The EOS token is now removed by default from the output, unrelated to the API.
- Resolved memory leaks caused by NCCL CUDA graphs.
- Improved garbage collection for LoRAs.
- Optimized the execution of embedded runtime scripts.

Upcoming Improvements

Here's a sneak peek at what we're working on for the next release:

- Investigating tensor parallelism with Exllamav2
- Addressing the issue of missing GPU blocks for GGUF and Exl2 (we already have a fix for FP16, GPTQ, and AWQ)

New Contributors
* anon998 made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/253
* sgsdxzy made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/256
* SwadicalRag made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/268
* thomas-xin made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/260
* StefanDanielSchwarz made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/264
* Pyroserenus made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/296
* Autumnlight02 made their first contribution in https://github.com/PygmalionAI/aphrodite-engine/pull/288


**Full Changelog**: https://github.com/PygmalionAI/aphrodite-engine/compare/v0.4.9...v0.5.0

Page 2 of 5

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.