Skip to content

Instantly share code, notes, and snippets.

View ryan4yin's full-sized avatar
📖
coding

ryan4yin | 二花 ryan4yin

📖
coding
1.2k followers · 510 following
View GitHub Profile
@ryan4yin
ryan4yin / uart.c
Created February 21, 2023 16:38 — forked from glegrain/uart.c
STM32 printf retarget to UART
/*# 1- Identify the UART interface, GPIO pins and Alternate Function #########*/
/* For example:
* B-L475E-IOT01A:
* PB6 ------> USART1_TX
* PB7 ------> USART1_RX
*
* NUCLEO-L476RG:
* PA2 ------> USART2_TX
* PA3 ------> USART2_RX
*
@ryan4yin
ryan4yin / config.yaml
Last active March 26, 2026 05:23
transparent proxy (mihomo tproxy + nftables)
# https://wiki.metacubex.one/en/example/conf/
######### 锚点 start #######
# 策略组相关
pr: &pr
type: select
proxies: [默认, 香港, 香港自动选择, 台湾, 台湾自动选择, 日本, 日本自动选择, 新加坡, 新加坡自动选择, 美国, 美国自动选择, 其它地区, 全部节点, 自动选择, 直连]
#这里是订阅更新和延迟测试相关的
p: &p
type: http
interval: 3600
@ryan4yin
ryan4yin / Qwen3.8-27B.md
Last active August 29, 2026 06:16
Qwen3.8-27B best llama.cpp config on RTX 4090 24GB (BeeLlama, UD-Q4_K_XL v3.0, kvarn6 + kv-tail 2048 @ 165K, MTP n-max 3, fit off)

Best llama.cpp config for Qwen3.8-27B (RTX 4090 24GB)

Quality-first setup (current 2026-08-28, matches docker-compose.qwen3.8-27b-xl.yml), measured on:

  • CPU: Intel Core Ultra 7 270K Plus (24C/24T, no HT)
  • RAM: 96GB DDR5-5600 (2x48GB dual channel, ≈89.6 GB/s theoretical bandwidth)
  • GPU: RTX 4090 24GB Use the BeeLlama fork image (server-cuda13-v0.4.3) — mainline llama.cpp silently falls back to CPU for non-q4 KV caches on Qwen3.x hybrid architecture (no error is reported).
@ryan4yin
ryan4yin / Qwen3.8-Flash-Next.md
Last active August 29, 2026 06:13
Best llama.cpp config for Qwen3.8-Flash-Next (RTX 4090 24GB)

Qwen3.8-Flash-Next — llama.cpp on RTX 4090 24GB

Platform:

  • CPU: Intel Core Ultra 7 270K Plus (24C/24T)
  • RAM: 96GB DDR5-5600 (2x48GB dual channel, ≈89.6 GB/s theoretical bandwidth)
  • GPU: RTX 4090 24GB

Model: unsloth/Qwen3.8-Flash-Next-GGUF, UD-IQ3_XXS (≈82GB, 76.3 GiB) + mmproj-F16 (≈900MB, vision enabled). llama.cpp mainline (ghcr.io/ggml-org/llama.cpp:full-cuda13). Final config as of 2026-08-29.