deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-07-05 07:51:38 -04:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

docs: Tidy root README, add hardware notes to experimental/README.md

Browse Source
This commit is contained in:
Triex 2025-06-11 17:48:38 +10:00
parent 0f980354f8
commit 7b81ea27d7
2 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -27,7 +27,7 @@ A **DRAFT proposal & foundation** for implementing DeepSeek V3 in Zig to create
- ✅ SIMD-optimized tensor operations (draft implementation) - ✅ SIMD-optimized tensor operations (draft implementation)
- ✅ Cross-platform backend architecture - ✅ Cross-platform backend architecture
- ✅ Initial memory management - ✅ Initial memory management
- ✅ **Apple Silicon M-series detection** (real hardware detection via sysctl) - ✅ **Apple Silicon M-series detection** (hardware detection via sysctl)
- ✅ Comprehensive build system draft - ✅ Comprehensive build system draft
- ⚠️ **NOT PRODUCTION READY** - Draft implementation for research/development - ⚠️ **NOT PRODUCTION READY** - Draft implementation for research/development
@ -157,7 +157,7 @@ Current LLM inference is dominated by Python/PyTorch, which introduces:
### For the Current Zig Implementation: ### For the Current Zig Implementation:
```bash ```bash
# Clone this repository # Clone this repository
git clone https://github.com/[current-repo-path] git clone https://github.com/Triex/DeepZig-V3
cd DeepSeek-V3-Zig/experimental cd DeepSeek-V3-Zig/experimental
# Build and test the foundation # Build and test the foundation

7
experimental/README.md
View File

@ -233,14 +233,17 @@ Run benchmarks to measure performance:
zig build bench zig build bench
``` ```
**Hardware Context**: Benchmarks run on Apple M1 MacBook Pro (MacBookPro17,1) with 16GB unified memory, Zig 0.15.0-dev.703+597dd328e, debug build.
Example output: Example output:
``` ```
🚀 DeepZig V3 Performance Benchmarks 🚀 DeepZig V3 Performance Benchmarks
========================================== ==========================================
Backend: CPU (SIMD optimized) Backend: CPU (SIMD optimized)
Architecture: x86_64 Architecture: aarch64
Thread count: 16 Thread count: 8
Hardware: Apple M1 MacBook Pro, 16GB unified memory
Operation | Iterations | Avg Time | Operations/s | Memory Operation | Iterations | Avg Time | Operations/s | Memory
-------------------------------|------------|-----------|--------------|------- -------------------------------|------------|-----------|--------------|-------