Update README

README.md

@@ -12,18 +12,19 @@
 > *It is built on the excellent work of [llama.cpp](https://github.com/ggerganov/llama.cpp), [bitsandbytes](https://github.com/TimDettmers/bitsandbytes), [qlora](https://github.com/artidoro/qlora), [gptq](https://github.com/IST-DASLab/gptq), [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), [awq](https://github.com/mit-han-lab/llm-awq), [AutoAWQ](https://github.com/casper-hansen/AutoAWQ), [vLLM](https://github.com/vllm-project/vllm), [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), [gptq_for_llama](https://github.com/qwopqwop200/GPTQ-for-LLaMa), [chatglm.cpp](https://github.com/li-plus/chatglm.cpp), [redpajama.cpp](https://github.com/togethercomputer/redpajama.cpp), [gptneox.cpp](https://github.com/byroneverson/gptneox.cpp), [bloomz.cpp](https://github.com/NouamaneTazi/bloomz.cpp/), etc.*
 
 ### Latest update 🔥 
-- [2024/02] `bigdl-llm` now supports *[Self-Speculative Decoding](https://bigdl.readthedocs.io/en/main/doc/LLM/Inference/Self_Speculative_Decoding.html)*, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel [GPU](python/llm/example/GPU/Speculative-Decoding) and [CPU](python/llm/example/CPU/Speculative-Decoding) respectively 
-- [2024/02] `bigdl-llm` now supports a comprehensive list of LLM finetuning on Intel GPU (including [LoRA](python/llm/example/GPU/LLM-Finetuning/LoRA), [QLoRA](python/llm/example/GPU/LLM-Finetuning/QLoRA), [DPO](python/llm/example/GPU/LLM-Finetuning/DPO), [QA-LoRA](python/llm/example/GPU/LLM-Finetuning/QA-LoRA) and [ReLoRA](python/llm/example/GPU/LLM-Finetuning/ReLora))
+- [2024/02] `bigdl-llm` now supports *[Self-Speculative Decoding](https://bigdl.readthedocs.io/en/main/doc/LLM/Inference/Self_Speculative_Decoding.html)*, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel [GPU](python/llm/example/GPU/Speculative-Decoding) and [CPU](python/llm/example/CPU/Speculative-Decoding) respectively.
+- [2024/02] `bigdl-llm` now supports a comprehensive list of LLM finetuning on Intel GPU (including [LoRA](python/llm/example/GPU/LLM-Finetuning/LoRA), [QLoRA](python/llm/example/GPU/LLM-Finetuning/QLoRA), [DPO](python/llm/example/GPU/LLM-Finetuning/DPO), [QA-LoRA](python/llm/example/GPU/LLM-Finetuning/QA-LoRA) and [ReLoRA](python/llm/example/GPU/LLM-Finetuning/ReLora)).
+- [2024/01] Using `bigdl-llm` [QLoRA](python/llm/example/GPU/LLM-Finetuning/QLoRA), we managed to finetune LLaMA2-7B in **21 minutes** and LLaMA2-70B in **3.14 hours** on 8 Intel Max 1550 GPU for [Standford-Alpaca](python/llm/example/GPU/LLM-Finetuning/QLoRA/alpaca-qlora) (see the blog [here](https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html)).
 - [2024/01] 🔔🔔🔔 ***The default `bigdl-llm` GPU Linux installation has switched from PyTorch 2.0 to PyTorch 2.1, which requires new oneAPI and GPU driver versions. (See the [GPU installation guide](https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/install_gpu.html) for more details.)***
-- [2023/12] `bigdl-llm` now supports [ReLoRA](python/llm/example/GPU/LLM-Finetuning/ReLora) (see *["ReLoRA: High-Rank Training Through Low-Rank Updates"](https://arxiv.org/abs/2307.05695)*)
+- [2023/12] `bigdl-llm` now supports [ReLoRA](python/llm/example/GPU/LLM-Finetuning/ReLora) (see *["ReLoRA: High-Rank Training Through Low-Rank Updates"](https://arxiv.org/abs/2307.05695)*).
 - [2023/12] `bigdl-llm` now supports [Mixtral-8x7B](python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral) on both Intel [GPU](python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral) and [CPU](python/llm/example/CPU/HF-Transformers-AutoModels/Model/mixtral).
-- [2023/12] `bigdl-llm` now supports [QA-LoRA](python/llm/example/GPU/LLM-Finetuning/QA-LoRA) (see *["QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models"](https://arxiv.org/abs/2309.14717)*)
+- [2023/12] `bigdl-llm` now supports [QA-LoRA](python/llm/example/GPU/LLM-Finetuning/QA-LoRA) (see *["QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models"](https://arxiv.org/abs/2309.14717)*).
 - [2023/12] `bigdl-llm` now supports [FP8 and FP4 inference](python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types) on Intel ***GPU***.
 - [2023/11] Initial support for directly loading [GGUF](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GGUF), [AWQ](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/AWQ) and [GPTQ](python/llm/example/GPU/HF-Transformers-AutoModels/Advanced-Quantizations/GPTQ) models into `bigdl-llm` is available.
 - [2023/11] `bigdl-llm` now supports [vLLM continuous batching](python/llm/example/GPU/vLLM-Serving) on both Intel [GPU](python/llm/example/GPU/vLLM-Serving) and [CPU](python/llm/example/CPU/vLLM-Serving).
 - [2023/10] `bigdl-llm` now supports [QLoRA finetuning](python/llm/example/GPU/LLM-Finetuning/QLoRA) on both Intel [GPU](python/llm/example/GPU/LLM-Finetuning/QLoRA) and [CPU](python/llm/example/CPU/QLoRA-FineTuning).
 - [2023/10] `bigdl-llm` now supports [FastChat serving](python/llm/src/bigdl/llm/serving) on on both Intel CPU and GPU.
-- [2023/09] `bigdl-llm` now supports [Intel GPU](python/llm/example/GPU) (including Arc, Flex and MAX)
+- [2023/09] `bigdl-llm` now supports [Intel GPU](python/llm/example/GPU) (including iGPU, Arc, Flex and MAX).
 - [2023/09] `bigdl-llm` [tutorial](https://github.com/intel-analytics/bigdl-llm-tutorial) is released.
 - [2023/09] Over 30 models have been optimized/verified on `bigdl-llm`, including *LLaMA/LLaMA2, ChatGLM2/ChatGLM3, Mistral, Falcon, MPT, LLaVA, WizardCoder, Dolly, Whisper, Baichuan/Baichuan2, InternLM, Skywork, QWen/Qwen-VL, Aquila, MOSS,* and more; see the complete list [here](#verified-models).
 

docs/readthedocs/source/doc/LLM/Inference/Self_Speculative_Decoding.md

@@ -7,7 +7,7 @@ In [speculative](https://arxiv.org/abs/2302.01318) [decoding](https://arxiv.org/
 Built on top of the concept of “[self-speculative decoding](https://arxiv.org/abs/2309.08168)”, BigDL-LLM can now accelerate the original FP16 or BF16 model ***without the need of a separate draft model or model finetuning***; instead, it automatically converts the original model to INT4, and uses the INT4 model as the draft model behind the scene. In practice, this brings ***~30% speedup*** for FP16 and BF16 LLM inference latency on Intel GPU and CPU respectively.
 
 ### Using BigDL-LLM Self-Speculative Decoding
-Please refer to BigDL-LLM self-speculative decoding code snippets below, and the complete [GPU](https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/Speculative-Decoding) and [CPU](https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/Speculative-Decoding) examples in the project repo.
+Please refer to BigDL-LLM self-speculative decoding code snippets below, and the detailed [GPU](https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/Speculative-Decoding) and [CPU](https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/Speculative-Decoding) examples in the project repo.
 
 ```python
 model = AutoModelForCausalLM.from_pretrained(model_path,

docs/readthedocs/source/index.rst

@@ -24,10 +24,11 @@ BigDL-LLM: low-Bit LLM library
 ============================================
 Latest update 🔥
 ============================================
-- [2024/02] ``bigdl-llm`` now supports `Self-Speculative Decoding <doc/LLM/Inference/Self_Speculative_Decoding.html>`_, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel `GPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/Speculative-Decoding>`_ and `CPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/Speculative-Decoding>`_ respectively
-- [2024/02] ``bigdl-llm`` now supports a comprehensive list of LLM finetuning on Intel GPU (including `LoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/LoRA>`_, `QLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QLoRA>`_, `DPO <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/DPO>`_, `QA-LoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QA-LoRA>`_ and `ReLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/ReLora>`_)
+- [2024/02] ``bigdl-llm`` now supports `Self-Speculative Decoding <doc/LLM/Inference/Self_Speculative_Decoding.html>`_, which in practice brings **~30% speedup** for FP16 and BF16 inference latency on Intel `GPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/Speculative-Decoding>`_ and `CPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/Speculative-Decoding>`_ respectively.
+- [2024/02] ``bigdl-llm`` now supports a comprehensive list of LLM finetuning on Intel GPU (including `LoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/LoRA>`_, `QLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QLoRA>`_, `DPO <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/DPO>`_, `QA-LoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QA-LoRA>`_ and `ReLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/ReLora>`_).
+- [2024/01] Using ``bigdl-llm`` `QLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QLoRA>`_, we managed to finetune LLaMA2-7B in **21 minutes** and LLaMA2-70B in **3.14 hours** on 8 Intel Max 1550 GPU for `Standford-Alpaca <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QLoRA/alpaca-qlora>`_ (see the blog `here <https://www.intel.com/content/www/us/en/developer/articles/technical/finetuning-llms-on-intel-gpus-using-bigdl-llm.html>`_).
 - [2024/01] 🔔🔔🔔 **The default** ``bigdl-llm`` **GPU Linux installation has switched from PyTorch 2.0 to PyTorch 2.1, which requires new oneAPI and GPU driver versions. (See the** `GPU installation guide <https://bigdl.readthedocs.io/en/latest/doc/LLM/Overview/install_gpu.html>`_ **for more details.)**
-- [2023/12] ``bigdl-llm`` now supports `ReLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/ReLora>`_ (see `"ReLoRA: High-Rank Training Through Low-Rank Updates" <https://arxiv.org/abs/2307.05695>`_)
+- [2023/12] ``bigdl-llm`` now supports `ReLoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/ReLora>`_ (see `"ReLoRA: High-Rank Training Through Low-Rank Updates" <https://arxiv.org/abs/2307.05695>`_).
 - [2023/12] ``bigdl-llm`` now supports `Mixtral-8x7B <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral>`_ on both Intel `GPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/HF-Transformers-AutoModels/Model/mixtral>`_ and `CPU <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/HF-Transformers-AutoModels/Model/mixtral>`_.
 - [2023/12] ``bigdl-llm`` now supports `QA-LoRA <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/LLM-Finetuning/QA-LoRA>`_ (see `"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models" <https://arxiv.org/abs/2309.14717>`_).
 - [2023/12] ``bigdl-llm`` now supports `FP8 and FP4 inference <https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/HF-Transformers-AutoModels/More-Data-Types>`_ on Intel **GPU**.