From cd50ba92faa5fde731b8a1372bafa439f7910617 Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Thu, 5 Dec 2024 11:16:22 +0800 Subject: [PATCH 1/4] Add NPU demo gif to main readme --- README.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index d202ac40a49..6159d905b39 100644 --- a/README.md +++ b/README.md @@ -78,20 +78,20 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing - - + +
Intel Iris iGPUIntel Core Ultra iGPUIntel Core Ultra (Series 1) iGPUIntel Core Ultra (Series 2) NPU Intel Arc dGPU 2-Card Intel Arc dGPUs
- - + + - - + + @@ -107,10 +107,10 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing
- llama.cpp (Phi-3-mini Q4_0) + Ollama (Mistral-7B Q4_K) - Ollama (Mistral-7B Q4_K) + NPU (Llama3.2-3B Q4_0) TextGeneration-WebUI (Llama3-8B FP8) From 11fb016c14f550712ee91e5448bc222f2c173482 Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Thu, 5 Dec 2024 11:21:51 +0800 Subject: [PATCH 2/4] Small fix --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6159d905b39..0d4c7669911 100644 --- a/README.md +++ b/README.md @@ -110,7 +110,7 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing Ollama (Mistral-7B Q4_K) - NPU (Llama3.2-3B Q4_0) + PyTorch (Llama3.2-3B SYM_INT4) TextGeneration-WebUI (Llama3-8B FP8) From 09b9d7a905508e7c17959af5124c39815388a200 Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Thu, 5 Dec 2024 12:13:10 +0800 Subject: [PATCH 3/4] Update based on comments --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0d4c7669911..e14fa7f55c0 100644 --- a/README.md +++ b/README.md @@ -110,7 +110,7 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing Ollama (Mistral-7B Q4_K) - PyTorch (Llama3.2-3B SYM_INT4) + HuggingFace (Llama3.2-3B SYM_INT4) TextGeneration-WebUI (Llama3-8B FP8) From abd2f0bf14bf8d2fc352d213960f3d760d3769e7 Mon Sep 17 00:00:00 2001 From: Yuwen Hu Date: Thu, 5 Dec 2024 12:15:50 +0800 Subject: [PATCH 4/4] Test on style fix --- README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index e14fa7f55c0..17bf1ef01b6 100644 --- a/README.md +++ b/README.md @@ -107,16 +107,16 @@ See demos of running local LLMs *on Intel Iris iGPU, Intel Core Ultra iGPU, sing
- Ollama (Mistral-7B Q4_K) + Ollama
(Mistral-7B Q4_K) 		- HuggingFace (Llama3.2-3B SYM_INT4) + HuggingFace
(Llama3.2-3B SYM_INT4) 		- TextGeneration-WebUI (Llama3-8B FP8) + TextGeneration-WebUI
(Llama3-8B FP8) 		- FastChat (QWen1.5-32B FP6) + FastChat
(QWen1.5-32B FP6)