From 1ae9c4bee96ba42ee32ec5881ec558b95cff4982 Mon Sep 17 00:00:00 2001 From: Yejin Seo Date: Wed, 24 Jun 2026 11:38:44 +0100 Subject: [PATCH 1/4] apply rename of the LLM project --- internal/catalog/data/catalog.json | 2 +- scripts/update_templates/github_sources.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/internal/catalog/data/catalog.json b/internal/catalog/data/catalog.json index afa82f72..575927d6 100644 --- a/internal/catalog/data/catalog.json +++ b/internal/catalog/data/catalog.json @@ -64,7 +64,7 @@ } } }, - "url": "https://github.com/Arm-Examples/topo-cpu-ai-chat.git", + "url": "https://github.com/Arm-Examples/topo-llama-web-ui.git", "ref": "4eeaca0d65d952d4555cf6ac9cbecf75884a3812" }, { diff --git a/scripts/update_templates/github_sources.json b/scripts/update_templates/github_sources.json index d66969ef..422757c4 100644 --- a/scripts/update_templates/github_sources.json +++ b/scripts/update_templates/github_sources.json @@ -1,6 +1,6 @@ [ {"repo": "Arm-Examples/topo-welcome", "sha": "8303e66db59a7a11e64877121f3db1b688d2011f"}, {"repo": "Arm-Examples/topo-lightbulb-moment", "sha": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7"}, - {"repo": "Arm-Examples/topo-cpu-ai-chat", "sha": "4eeaca0d65d952d4555cf6ac9cbecf75884a3812"}, + {"repo": "Arm-Examples/topo-llama-web-ui", "sha": "4eeaca0d65d952d4555cf6ac9cbecf75884a3812"}, {"repo": "Arm-Examples/topo-simd-visual-benchmark", "sha": "f0cd31621ce79b4643df7e9bdd8eff26c20b338c"} ] From 80d0b884be2d02f8ba2667ff5ca5c4b370308a9f Mon Sep 17 00:00:00 2001 From: Yejin Seo Date: Thu, 25 Jun 2026 09:56:26 +0100 Subject: [PATCH 2/4] Update llama web UI catalog entry --- internal/catalog/data/catalog.json | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/internal/catalog/data/catalog.json b/internal/catalog/data/catalog.json index 575927d6..3a0b516e 100644 --- a/internal/catalog/data/catalog.json +++ b/internal/catalog/data/catalog.json @@ -42,18 +42,10 @@ "ref": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7" }, { - "name": "Topo CPU AI Chat", - "description": "Complete LLM chat application optimized for Arm CPU inference.\n\nThis project demonstrates running large language models on CPU\nusing llama.cpp compiled with Arm baseline optimizations and\naccelerated using NEON SIMD and SVE (when supported and enabled).\n\nThe stack includes:\n- llama.cpp server with Arm NEON optimizations (SVE optional)\n- Quantized SmolLM2-135M-Instruct model bundled in the image\n- Simple web-based chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The bundled SmolLM2-135M-Instruct model\nallows the project to run immediately without downloading additional models.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies,\nshowcasing how far you can push NEON acceleration. Rebuild with SVE enabled\nwhen wider vectors are available.\n", - "features": [ - "SVE", - "NEON" - ], + "name": "Topo llama web UI Chat", + "description": "LLM chat application with Arm CPU inference provided by llama.cpp.\n\nThis project demonstrates running large language models on CPU\nwith inference provided by the llama.cpp server.\n\nThe upstream Linux Arm64 image includes architecture-specific CPU\nbackend variants for Armv8.0 baseline, Armv8.2 dot product/FP16/SVE,\nArmv8.6 int8 matrix multiply/SVE2, and Armv9.2 SME-capable CPUs.\n\nThe stack includes:\n- llama.cpp\n- Quantized SmolLM2 135M default model loaded through llama.cpp\n- Built-in web chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The default SmolLM2-135M-Instruct model\ngives the project a small ready-to-use model reference by default.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies\nwhile avoiding a source build during Template deployment.", + "features": [], "args": { - "ENABLE_SVE": { - "description": "Enables building with SVE instructions (OFF/ON)", - "default": "OFF", - "example": "ON" - }, "MODEL": { "description": "Model artifact reference. Use a Hugging Face GGUF repo ID, repo ID plus filename separated by ':', or a direct .gguf URL.", "default": "unsloth/SmolLM2-135M-Instruct-GGUF", From 8028649053e7496f394d39bb7d980ca584aecd81 Mon Sep 17 00:00:00 2001 From: Yejin Seo Date: Thu, 25 Jun 2026 10:19:23 +0100 Subject: [PATCH 3/4] update the SHA and catalog --- internal/catalog/data/catalog.json | 8 ++++---- scripts/update_templates/github_sources.json | 2 +- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/internal/catalog/data/catalog.json b/internal/catalog/data/catalog.json index 3a0b516e..0b85b255 100644 --- a/internal/catalog/data/catalog.json +++ b/internal/catalog/data/catalog.json @@ -42,9 +42,9 @@ "ref": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7" }, { - "name": "Topo llama web UI Chat", - "description": "LLM chat application with Arm CPU inference provided by llama.cpp.\n\nThis project demonstrates running large language models on CPU\nwith inference provided by the llama.cpp server.\n\nThe upstream Linux Arm64 image includes architecture-specific CPU\nbackend variants for Armv8.0 baseline, Armv8.2 dot product/FP16/SVE,\nArmv8.6 int8 matrix multiply/SVE2, and Armv9.2 SME-capable CPUs.\n\nThe stack includes:\n- llama.cpp\n- Quantized SmolLM2 135M default model loaded through llama.cpp\n- Built-in web chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The default SmolLM2-135M-Instruct model\ngives the project a small ready-to-use model reference by default.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies\nwhile avoiding a source build during Template deployment.", - "features": [], + "name": "Topo CPU AI Chat", + "description": "Complete LLM chat application optimized for Arm CPU inference.\n\nThis project demonstrates running large language models on CPU\nusing the llama.cpp server image.\n\nThe upstream Linux Arm64 image includes architecture-specific CPU\nbackend variants for Armv8.0 baseline, Armv8.2 dot product/FP16/SVE,\nArmv8.6 int8 matrix multiply/SVE2, and Armv9.2 SME-capable CPUs.\n\nThe stack includes:\n- llama.cpp\n- Quantized SmolLM2 135M default model loaded through llama.cpp\n- Built-in web chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The default SmolLM2-135M-Instruct model\ngives the project a small ready-to-use model reference by default.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies\nwhile avoiding a source build during Template deployment.\n", + "features": null, "args": { "MODEL": { "description": "Model artifact reference. Use a Hugging Face GGUF repo ID, repo ID plus filename separated by ':', or a direct .gguf URL.", @@ -57,7 +57,7 @@ } }, "url": "https://github.com/Arm-Examples/topo-llama-web-ui.git", - "ref": "4eeaca0d65d952d4555cf6ac9cbecf75884a3812" + "ref": "8831efd5901e0bc0cf4aacb28e8c74792287349a" }, { "name": "SIMD Visual Benchmark", diff --git a/scripts/update_templates/github_sources.json b/scripts/update_templates/github_sources.json index 422757c4..3450a7da 100644 --- a/scripts/update_templates/github_sources.json +++ b/scripts/update_templates/github_sources.json @@ -1,6 +1,6 @@ [ {"repo": "Arm-Examples/topo-welcome", "sha": "8303e66db59a7a11e64877121f3db1b688d2011f"}, {"repo": "Arm-Examples/topo-lightbulb-moment", "sha": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7"}, - {"repo": "Arm-Examples/topo-llama-web-ui", "sha": "4eeaca0d65d952d4555cf6ac9cbecf75884a3812"}, + {"repo": "Arm-Examples/topo-llama-web-ui", "sha": "8831efd5901e0bc0cf4aacb28e8c74792287349a"}, {"repo": "Arm-Examples/topo-simd-visual-benchmark", "sha": "f0cd31621ce79b4643df7e9bdd8eff26c20b338c"} ] From e66ac43f4b8b761cf914d07a1f3aa5f68684336e Mon Sep 17 00:00:00 2001 From: Yejin Seo Date: Thu, 25 Jun 2026 15:18:30 +0100 Subject: [PATCH 4/4] update catalog again --- internal/catalog/data/catalog.json | 6 +++--- scripts/update_templates/github_sources.json | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/internal/catalog/data/catalog.json b/internal/catalog/data/catalog.json index 0b85b255..759af4e7 100644 --- a/internal/catalog/data/catalog.json +++ b/internal/catalog/data/catalog.json @@ -42,8 +42,8 @@ "ref": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7" }, { - "name": "Topo CPU AI Chat", - "description": "Complete LLM chat application optimized for Arm CPU inference.\n\nThis project demonstrates running large language models on CPU\nusing the llama.cpp server image.\n\nThe upstream Linux Arm64 image includes architecture-specific CPU\nbackend variants for Armv8.0 baseline, Armv8.2 dot product/FP16/SVE,\nArmv8.6 int8 matrix multiply/SVE2, and Armv9.2 SME-capable CPUs.\n\nThe stack includes:\n- llama.cpp\n- Quantized SmolLM2 135M default model loaded through llama.cpp\n- Built-in web chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The default SmolLM2-135M-Instruct model\ngives the project a small ready-to-use model reference by default.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies\nwhile avoiding a source build during Template deployment.\n", + "name": "Topo llama.cpp WebUI Chat", + "description": "LLM chat application with Arm CPU inference provided by llama.cpp.\n\nThis project demonstrates running large language models on CPU\nwith inference provided by the llama.cpp server.\n\nThe upstream Linux Arm64 image includes architecture-specific CPU\nbackend variants for Armv8.0 baseline, Armv8.2 dot product/FP16/SVE,\nArmv8.6 int8 matrix multiply/SVE2, and Armv9.2 SME-capable CPUs.\n\nThe stack includes:\n- llama.cpp\n- Quantized SmolLM2 135M default model loaded through llama.cpp\n- Built-in web chat interface\n- No GPU required - pure CPU inference\n\nPerfect for demos and testing! The default SmolLM2-135M-Instruct model\ngives the project a small ready-to-use model reference by default.\n\nIdeal for testing LLM workloads on Arm hardware without GPU dependencies\nwhile avoiding a source build during Template deployment.\n", "features": null, "args": { "MODEL": { @@ -57,7 +57,7 @@ } }, "url": "https://github.com/Arm-Examples/topo-llama-web-ui.git", - "ref": "8831efd5901e0bc0cf4aacb28e8c74792287349a" + "ref": "99561df2838081fc7f7af9229b8e677b898bbd88" }, { "name": "SIMD Visual Benchmark", diff --git a/scripts/update_templates/github_sources.json b/scripts/update_templates/github_sources.json index 3450a7da..abff6c65 100644 --- a/scripts/update_templates/github_sources.json +++ b/scripts/update_templates/github_sources.json @@ -1,6 +1,6 @@ [ {"repo": "Arm-Examples/topo-welcome", "sha": "8303e66db59a7a11e64877121f3db1b688d2011f"}, {"repo": "Arm-Examples/topo-lightbulb-moment", "sha": "c2b2e4a672cda67832372f77aeb1d1f71beee9a7"}, - {"repo": "Arm-Examples/topo-llama-web-ui", "sha": "8831efd5901e0bc0cf4aacb28e8c74792287349a"}, + {"repo": "Arm-Examples/topo-llama-web-ui", "sha": "99561df2838081fc7f7af9229b8e677b898bbd88"}, {"repo": "Arm-Examples/topo-simd-visual-benchmark", "sha": "f0cd31621ce79b4643df7e9bdd8eff26c20b338c"} ]