LM: Difference between revisions

From Fundamental Ramen
Jump to navigation Jump to search
← Older edit
VisualWikitext
 
(155 intermediate revisions by the same user not shown)
Line 1: Line 1:
= Decision Tree for tinkering with Intel Arc Pro B70 =
= Topics =


<quickmmd name="tinkering-b70">
{| class="wikitable"
! 🤖 Agent　 || 🧠 Model　 || 🚀 Engine　 || ⚙️ GPU & Driver　|| 📊 Evaluation
|-
| style="width:200px;vertical-align:top" |
: [[LM/ZooCode|ZooCode]]
: [[LM/jrswab_axe|axe]]
: [[LM/MCP|MCP]]
| style="width:200px;vertical-align:top" |
: [[LM/hf|hf (Model Management)]]
: [[LM/Qwen Image 2.1|Qwen Image 2.1]]
: [[LM/Bonsai 2 27B|Bonsai 2 27B]]
: [[LM/Qwen 3.8 27B|Qwen 3.8 27B]]
: [[LM/Gemma 4|Gemma 4]]
: [[LM/Devstral Small 2 24B|Devstral Small 2 24B]]
: [[LM/Experience|Experience]]
| style="width:200px;vertical-align:top" |
: [[LM/vLLM|vLLM]]
: [[LM/llama-swap|llama-swap]]
: [[LM/ComfyUI|ComfyUI]]
: [[LM/llama.cpp for SYCL|llama.cpp for SYCL]]
: [[LM/llama.cpp for CUDA|llama.cpp for CUDA]]
: [[LM/llama.cpp for OpenVINO|llama.cpp for OpenVINO]]
: [[LM/llama.cpp for TurboQuant|llama.cpp for TurboQuant]]
: [[LM/SGLang|SGLang]]
| style="width:200px;vertical-align:top" |
: Intel Arc Pro B70
:: [[LM/Install driver|Install driver]]
:: [[LM/Install oneAPI|Install oneAPI (SYCL)]]
:: [[LM/Install OpenVINO|Install OpenVINO]]
:: [[LM/.bashrc for B70|.bashrc for B70]]
:: [[LM/Intel Pro Arc B70|Experiment]]
: NVIDIA RTX 3060
:: [[LM/Install NVIDIA driver|Install driver]]
: AMD Ryzen AI 7 350
:: [[LM/Ryzen AI 7 350|Experiment]]
: Tools
:: [[LM/Install nvtop|Install nvtop]]
:: [[LM/PCIe Trouble Shooting|PCIe Trouble Shooting]]
: Comparison
:: [[LM/GPU Comparison]]
| style="width:200px;vertical-align:top" |
: [[LM/Performance|Performance]]
|}
 
= News =
 
* [https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro?leaderboard_max_params=32B SWE Pro Benchmark for models < 32B]
* [https://storage.openvinotoolkit.org/repositories/openvino/packages/2026.3/linux/ OpenVINO 2026.3 supports Ubuntu 26] - 2026-08-04
 
= Models management =
 
<quickmmd name="models-handling-infra">
flowchart LR
flowchart LR
   subgraph zero
   A(LiteLLM)
    A[Got B70]
  B(vLLM<br>Qwen 3.8 27B)
   end
  C1(Intel Arc Pro B70)
   C2(Intel Arc Pro B70)


   subgraph os
   A --> |Forward| B
    B1[Install Ubuntu 24.04]
  B --> |Tensor Parallelism| C1 & C2
    B2[Install Ubuntu 26.04]
   C1 --- |XCCL| C2
    A --> B1
    A --> B2
   end
</quickmmd>
</quickmmd>


= Build environment =
* llama-swap can launch model, cannot manage users.
* LiteLLM cannot launch model, can manage users.
 
= Investigating llama.cpp on Intel Arc Pro B70 =
 
<quickmmd name="tinkering-b70">
flowchart TD
  subgraph Hardware
    A1(Intel Arc Pro B70):::node-okay
    A2(Asus ProArt B850 WiFi NEO):::node-okay
    A3(AMD Ryzen 5 9600X):::node-okay
  end


== hf (model management) ==
  subgraph OS
* https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables
    B1(Install<br>Ubuntu 26.04):::node-okay
* https://www.datalearner.com/en/leaderboards/category/code?benchmark=SWE-bench+Verified&modelSize=34b&licenseType=open
    A1 & A2 & A3 --> B1
* https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro
  end


{| class="wikitable"
  subgraph Driver
! Purpose || Command
    C1(Install PPA driver<br>26.27.39122.14):::node-okay
|-
    C2(Install oneAPI<br>2026.1.1.20260724):::node-okay
| cache management ||
    C1 --> C2
<syntaxhighlight lang="bash">
    B1 --> C1
hf cache list
  end
hf cache rm <model id>
hf cache prune
</syntaxhighlight>
|-
| fix WiFi problem ||
<syntaxhighlight lang="bash">
HF_XET_FIXED_DOWNLOAD_CONCURRENCY=10 hf download "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF" --include "*UD-Q4_K_XL*"
HF_XET_FIXED_DOWNLOAD_CONCURRENCY=10 hf download "unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF" --include "*UD-Q4_K_XL*"
</syntaxhighlight>
|-
| search ||
<syntaxhighlight lang="bash">
hf models ls --search "gemma-4" --apps llama.cpp --sort downloads --limit 10
hf models ls --search "coder" --apps llama.cpp --sort downloads --limit 10
hf models ls --search "unsloth" --apps llama.cpp --sort downloads --limit 10
</syntaxhighlight>
|-
| optimize Qwen3-Coder ||
<syntaxhighlight lang="bash">
hf models ls --search "coder" --apps llama.cpp --sort downloads --limit 1 --format json | jq .
hf models ls -h "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF"
hf download "unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF" --include "*UD-Q4_K_XL*"
</syntaxhighlight>
|-
| optimize gemma-4-E4B ||
<syntaxhighlight lang="bash">
hf models ls -h unsloth/gemma-4-E4B-it-qat-GGUF
hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "*UD-Q4_K_XL*"
hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "mmproj-BF16.gguf"
hf download unsloth/gemma-4-E4B-it-qat-GGUF --include "mtp-gemma-4-E4B-it.gguf"
</syntaxhighlight>
|-
| optimize gemma-4-12B ||
<syntaxhighlight lang="bash">
hf models ls -h unsloth/gemma-4-12B-it-qat-GGUF
hf download unsloth/gemma-4-12B-it-qat-GGUF --include "*UD-Q4_K_XL*"
hf download unsloth/gemma-4-12B-it-qat-GGUF --include "mmproj-BF16.gguf"
hf download unsloth/gemma-4-12B-it-qat-GGUF --include "mtp-gemma-4-12B-it.gguf"
</syntaxhighlight>
|-
| optimize Muse Glimmer ||
<syntaxhighlight lang="bash">
hf models ls -h unsloth/Muse-Glimmer-30B-GGUF
hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q4_K_XL*"
hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q5_K_XL*"
hf download unsloth/Muse-Glimmer-30B-GGUF --include "*UD-Q6_K_XL*"
hf download unsloth/Muse-Glimmer-30B-GGUF --include "dflash-kquant.gguf"
hf download unsloth/Muse-Glimmer-30B-GGUF --include "mmproj-kquant.gguf"
</syntaxhighlight>
|-
|  ||
<syntaxhighlight lang="bash">
tree ~/.cache/huggingface/hub/models--unsloth--Devstral-Small-2-24B-Instruct-2512-GGUF/snapshots
tree ~/.cache/huggingface/hub/models--unsloth--Qwen3-Coder-30B-A3B-Instruct-GGUF/snapshots
</syntaxhighlight>
|}


== Ubuntu ==
  subgraph Runtime
    D1[Build llama.cpp for<br>SYCL]:::node-okay
    C2 --> D1
  end


* [[LLM/Intel Pro Arc B70]]
  subgraph Tools
* [[LLM/Ryzen AI 7 350]] (XDNA)
    T1(Install<br>pipx)
    T2(Install<br>hf)
    T3(Install<br>nvtop)
    T4(Install<br>tmux)
    T5(Install<br>lact)
    T6(Install<br>llama-swap)
    T1 --> T2
    B1 --> T1
    B1 --> T3
    B1 --> T4
    B1 --> T5
    T5 --> T6
  end


== Agents ==
  subgraph Models
    M1(Qwen3.8-27B)
    T2 --> M1
  end


* [[LLM/jrswab_axe]]
  subgraph config
    V1(Optimize<br>.bashrc)
    V2(Optimize<br>lmsw.yaml)
    C2 --> V1
    T2 --> V1
    T4 ----> V1
    T6 ---> V2
  end


== Wishlist ==
  subgraph Service
    Z(service<br>llama-swap \<br>  -config lmsw.yaml \<br>  -listen 0.0.0.0:9876)
    M1 --> Z
    D1 --> Z
    V2 --> Z
  end


* [[LLM/prompt for coding]]
  classDef node-okay fill:#efe,stroke:#393
  classDef node-warn fill:#fff0e0,stroke:#d63
  classDef node-fail fill:#fee,stroke:#d33
  classDef node-todo fill:#eee,stroke:#777
</quickmmd>

Latest revision as of 03:12, 2 October 2026

Topics

🤖 Agent　 🧠 Model　 🚀 Engine　 ⚙️ GPU & Driver　 📊 Evaluation
ZooCode
axe
MCP
hf (Model Management)
Qwen Image 2.1
Bonsai 2 27B
Qwen 3.8 27B
Gemma 4
Devstral Small 2 24B
Experience
vLLM
llama-swap
ComfyUI
llama.cpp for SYCL
llama.cpp for CUDA
llama.cpp for OpenVINO
llama.cpp for TurboQuant
SGLang
Intel Arc Pro B70
Install driver
Install oneAPI (SYCL)
Install OpenVINO
.bashrc for B70
Experiment
NVIDIA RTX 3060
Install driver
AMD Ryzen AI 7 350
Experiment
Tools
Install nvtop
PCIe Trouble Shooting
Comparison
LM/GPU Comparison
Performance

News

Models management

  • llama-swap can launch model, cannot manage users.
  • LiteLLM cannot launch model, can manage users.

Investigating llama.cpp on Intel Arc Pro B70

Retrieved from "http://192.168.25.90:53000/index.php?title=LM&oldid=3774"