From 4778d4249e61004b3f94c31a4b7c8f42f248ca81 Mon Sep 17 00:00:00 2001
From: Amit Raj <168538872+quic-amitraj@users.noreply.github.com>
Date: Thu, 24 Oct 2024 15:11:55 +0530
Subject: [PATCH] Jenkins and Docs minor bug fix (#162)

* Added QEFF_HOME for CI setup

Signed-off-by: amitraj <quic_amitraj@quicinc.com>

* fixed broken links and updated

Signed-off-by: amitraj <quic_amitraj@quicinc.com>

---------

Signed-off-by: amitraj <quic_amitraj@quicinc.com>
---
 README.md                   |  5 ++++-
 docs/source/introduction.md | 12 ++++++++++--
 scripts/Jenkinsfile         |  1 +
 3 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 4f22ce3f..debb4eef 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,8 @@
 *Latest news* :fire: <br>
 
 - [coming soon] Support for more popular [models](https://quic.github.io/efficient-transformers/source/validate.html#models-coming-soon) and inference optimization technique speculative decoding <br>
+- [09/2024] [AWQ](https://arxiv.org/abs/2306.00978)/[GPTQ](https://arxiv.org/abs/2210.17323) 4-bit quantized models are supported
+- [09/2024] Now we support [PEFT](https://huggingface.co/docs/peft/index) models
 - [09/2024] Added support for [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)
 - [09/2024] Added support for [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
 - [09/2024] Added support for [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
@@ -27,6 +29,7 @@
 - [05/2024] Added support for [Mixtral-8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) & [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1).
 - [04/2024] Initial release of [efficient transformers](https://github.com/quic/efficient-transformers) for seamless inference on pre-trained LLMs.
 
+
 # Overview
 
 ## Train anywhere, Infer on Qualcomm Cloud AI with a Developer-centric Toolchain
@@ -77,7 +80,7 @@ For more details about using ``QEfficient`` via Cloud AI 100 Apps SDK, visit [Li
 * [Quick Start Guide](https://quic.github.io/efficient-transformers/source/quick_start.html#)
 * [Python API](https://quic.github.io/efficient-transformers/source/hl_api.html)
 * [Validated Models](https://quic.github.io/efficient-transformers/source/validate.html)
-* [Models coming soon](models-coming-soon)
+* [Models coming soon](https://quic.github.io/efficient-transformers/source/validate.html#models-coming-soon)
 
 > Note: More details are here: https://quic.github.io/cloud-ai-sdk-pages/latest/Getting-Started/Model-Architecture-Support/Large-Language-Models/llm/
 
diff --git a/docs/source/introduction.md b/docs/source/introduction.md
index 2e72b97a..a6f0140a 100644
--- a/docs/source/introduction.md
+++ b/docs/source/introduction.md
@@ -22,8 +22,16 @@ For other models, there is comprehensive documentation to inspire upon the chang
 
 ***Latest news*** : <br>
 
-- [coming soon] Support for more popular [models](coming_soon_models) and inference optimization technique speculative decoding <br>
-- [08/2024] Added Support for inference optimization technique ```continuous batching```
+- [coming soon] Support for more popular [models](https://quic.github.io/efficient-transformers/source/validate.html#models-coming-soon) and inference optimization technique speculative decoding <br>
+- [09/2024] [AWQ](https://arxiv.org/abs/2306.00978)/[GPTQ](https://arxiv.org/abs/2210.17323) 4-bit quantized models are supported
+- [09/2024] Now we support [PEFT](https://huggingface.co/docs/peft/index) models
+- [09/2024] Added support for [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B)
+- [09/2024] Added support for [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+- [09/2024] Added support for [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
+- [09/2024] Added support for [granite-20b-code-base](https://huggingface.co/ibm-granite/granite-20b-code-base-8k)
+- [09/2024] Added support for [granite-20b-code-instruct-8k](https://huggingface.co/ibm-granite/granite-20b-code-instruct-8k)
+- [09/2024] Added support for [Starcoder1-15B](https://huggingface.co/bigcode/starcoder)
+- [08/2024] Added support for inference optimization technique ```continuous batching```
 - [08/2024] Added support for [Jais-adapted-70b](https://huggingface.co/inceptionai/jais-adapted-70b)
 - [08/2024] Added support for [Jais-adapted-13b-chat](https://huggingface.co/inceptionai/jais-adapted-13b-chat)
 - [08/2024] Added support for [Jais-adapted-7b](https://huggingface.co/inceptionai/jais-adapted-7b)
diff --git a/scripts/Jenkinsfile b/scripts/Jenkinsfile
index 3facc515..b6e706fe 100644
--- a/scripts/Jenkinsfile
+++ b/scripts/Jenkinsfile
@@ -36,6 +36,7 @@ pipeline
                     sh '''
                     . preflight_qeff/bin/activate
                     export TOKENIZERS_PARALLELISM=false
+                    export QEFF_HOME=$PWD  
                     pytest tests --ignore tests/cloud --junitxml=tests/tests_log1.xml
                     pytest tests/cloud --junitxml=tests/tests_log2.xml
                     junitparser merge tests/tests_log1.xml tests/tests_log2.xml tests/tests_log.xml