intel/neural-speed issues and pull requests

#100 - [LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#100 - [LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#100 - [LLM Runtime] Support 3bits & 4bits GPTQ for gpt-j

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#99 - [Feature request] Add nllb support

Issue - State: closed - Opened by bil-ash 10 months ago - 4 comments

#99 - [Feature request] Add nllb support

Issue - State: closed - Opened by bil-ash 10 months ago - 4 comments

#99 - [Feature request] Add nllb support

Issue - State: closed - Opened by bil-ash 10 months ago - 4 comments

#98 - [Xetla]Arc sdp

Pull Request - State: closed - Opened by sunjiweiswift 10 months ago - 1 comment
Labels: XeTLA

#98 - [Xetla]Arc sdp

Pull Request - State: closed - Opened by sunjiweiswift 10 months ago - 1 comment
Labels: XeTLA

#98 - [Xetla]Arc sdp

Pull Request - State: closed - Opened by sunjiweiswift 10 months ago - 1 comment
Labels: XeTLA

#97 - Yarn feature

Pull Request - State: closed - Opened by xiguiw 10 months ago

#97 - Yarn feature

Pull Request - State: closed - Opened by xiguiw 10 months ago

#97 - Yarn feature

Pull Request - State: closed - Opened by xiguiw 10 months ago

#96 - Error loading model when use qwen gguf model

Issue - State: closed - Opened by kunger97 10 months ago - 7 comments

#96 - Error loading model when use qwen gguf model

Issue - State: closed - Opened by kunger97 10 months ago - 7 comments

#96 - Error loading model when use qwen gguf model

Issue - State: closed - Opened by kunger97 10 months ago - 7 comments

#95 - Update README.md

Pull Request - State: closed - Opened by hshen14 10 months ago

#95 - Update README.md

Pull Request - State: closed - Opened by hshen14 10 months ago

#95 - Update README.md

Pull Request - State: closed - Opened by hshen14 10 months ago

#94 - Low text quality when inferencing a gguf model with Neural Speed vs llama.cpp

Issue - State: closed - Opened by aahouzi 10 months ago - 5 comments

#94 - Low text quality when inferencing a gguf model with Neural Speed vs llama.cpp

Issue - State: closed - Opened by aahouzi 10 months ago - 5 comments

#94 - Low text quality when inferencing a gguf model with Neural Speed vs llama.cpp

Issue - State: closed - Opened by aahouzi 10 months ago - 5 comments

#93 - [LLM Runtime] Support loading models from HF directly.

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#93 - [LLM Runtime] Support loading models from HF directly.

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#93 - [LLM Runtime] Support loading models from HF directly.

Pull Request - State: closed - Opened by Zhenzhong1 10 months ago

#92 - [Neural Speed] Fix a blocker on Windows platforms

Pull Request - State: closed - Opened by aahouzi 10 months ago
Labels: ready to merge

#92 - [Neural Speed] Fix a blocker on Windows platforms

Pull Request - State: closed - Opened by aahouzi 10 months ago
Labels: ready to merge

#92 - [Neural Speed] Fix a blocker on Windows platforms

Pull Request - State: closed - Opened by aahouzi 10 months ago
Labels: ready to merge

#91 - error running inference

Issue - State: closed - Opened by RachelShalom 10 months ago - 3 comments

#91 - error running inference

Issue - State: closed - Opened by RachelShalom 10 months ago - 3 comments

#91 - error running inference

Issue - State: closed - Opened by RachelShalom 10 months ago - 3 comments

#90 - Error at Colab Inference of neural-chat-7b-v3-1 Model

Issue - State: closed - Opened by dopc 10 months ago - 3 comments

#90 - Error at Colab Inference of neural-chat-7b-v3-1 Model

Issue - State: closed - Opened by dopc 10 months ago - 3 comments

#90 - Error at Colab Inference of neural-chat-7b-v3-1 Model

Issue - State: closed - Opened by dopc 10 months ago - 3 comments

#89 - Cont batching mha++

Pull Request - State: closed - Opened by VincyZhang 10 months ago
Labels: won't merge

#89 - Cont batching mha++

Pull Request - State: closed - Opened by VincyZhang 10 months ago
Labels: won't merge

#89 - Cont batching mha++

Pull Request - State: closed - Opened by VincyZhang 10 months ago
Labels: won't merge

#88 - Can't inference Llama2 through GGUF

Issue - State: closed - Opened by ZJkyle 10 months ago - 2 comments

#88 - Can't inference Llama2 through GGUF

Issue - State: closed - Opened by ZJkyle 10 months ago - 2 comments

#88 - Can't inference Llama2 through GGUF

Issue - State: closed - Opened by ZJkyle 10 months ago - 2 comments

#87 - [Neural Speed] Improvements to run.py script

Pull Request - State: closed - Opened by aahouzi 10 months ago

#87 - [Neural Speed] Improvements to run.py script

Pull Request - State: closed - Opened by aahouzi 10 months ago

#87 - [Neural Speed] Improvements to run.py script

Pull Request - State: closed - Opened by aahouzi 10 months ago

#86 - load processed model automatically

Pull Request - State: closed - Opened by zhenwei-intel 10 months ago

#86 - load processed model automatically

Pull Request - State: closed - Opened by zhenwei-intel 10 months ago

#86 - load processed model automatically

Pull Request - State: closed - Opened by zhenwei-intel 10 months ago

#85 - 3bit weight in BesTLA

Pull Request - State: closed - Opened by zhewang1-intc 10 months ago
Labels: won't merge

#85 - 3bit weight in BesTLA

Pull Request - State: closed - Opened by zhewang1-intc 10 months ago
Labels: won't merge

#85 - 3bit weight in BesTLA

Pull Request - State: closed - Opened by zhewang1-intc 10 months ago
Labels: won't merge

#84 - update qwen python api

Pull Request - State: closed - Opened by zhenwei-intel 10 months ago - 1 comment

#84 - update qwen python api

Pull Request - State: closed - Opened by zhenwei-intel 10 months ago - 1 comment