mirror of
https://github.com/kvcache-ai/ktransformers.git
synced 2026-04-29 18:51:15 +00:00
* refactor: move legacy code to archive/ directory - Moved ktransformers, csrc, third_party, merge_tensors to archive/ - Moved build scripts and configurations to archive/ - Kept kt-kernel, KT-SFT, doc, and README files in root - Preserved complete git history for all moved files * refactor: restructure repository to focus on kt-kernel and KT-SFT modules * fix README * fix README * fix README * fix README * docs: add performance benchmarks to kt-kernel section Add comprehensive performance data for kt-kernel to match KT-SFT's presentation: - AMX kernel optimization: 21.3 TFLOPS (3.9× faster than PyTorch) - Prefill phase: up to 20× speedup vs baseline - Decode phase: up to 4× speedup - NUMA optimization: up to 63% throughput improvement - Multi-GPU (8×L20): 227.85 tokens/s total throughput with DeepSeek-R1 FP8 Source: https://lmsys.org/blog/2025-10-22-KTransformers/ This provides users with concrete performance metrics for both core modules, making it easier to understand the capabilities of each component. * refactor: improve kt-kernel performance data with specific hardware and models Replace generic performance descriptions with concrete benchmarks: - Specify exact hardware: 8×L20 GPU + Xeon Gold 6454S, Single/Dual-socket Xeon + AMX - Include specific models: DeepSeek-R1-0528 (FP8), DeepSeek-V3 (671B) - Show detailed metrics: total throughput, output throughput, concurrency details - Match KT-SFT presentation style for consistency This provides users with actionable performance data they can use to evaluate hardware requirements and expected performance for their use cases. * fix README * docs: clean up performance table and improve formatting * add pic for README * refactor: simplify .gitmodules and backup legacy submodules - Remove 7 legacy submodules from root .gitmodules (archive/third_party/*) - Keep only 2 active submodules for kt-kernel (llama.cpp, pybind11) - Backup complete .gitmodules to archive/.gitmodules - Add documentation in archive/README.md for researchers who need legacy submodules This reduces initial clone size by ~500MB and avoids downloading unused dependencies. * refactor: move doc/ back to root directory Keep documentation in root for easier access and maintenance. * refactor: consolidate all images to doc/assets/ - Move kt-kernel/assets/heterogeneous_computing.png to doc/assets/ - Remove KT-SFT/assets/ (images already in doc/assets/) - Update KT-SFT/README.md image references to ../doc/assets/ - Eliminates ~7.9MB image duplication - Centralizes all documentation assets in one location * fix pic path for README
36 lines
1019 B
Bash
Executable File
36 lines
1019 B
Bash
Executable File
#!/bin/bash
|
|
|
|
# 检查是否提供了 disk_cache_path 参数
|
|
if [ -z "$1" ]; then
|
|
echo "Usage: $0 <disk_cache_path>"
|
|
exit 1
|
|
fi
|
|
|
|
# 将 disk_cache_path 参数赋值给变量
|
|
disk_cache_path=$1
|
|
|
|
# 定义测试命令数组,并使用变量替换 disk_cache_path
|
|
tests=(
|
|
"./build/test/kvc2_export_header_test --disk_cache_path=$disk_cache_path"
|
|
"./build/test/kvcache_disk_insert_read_test --disk_cache_path=$disk_cache_path"
|
|
"./build/test/kvcache_mem_eviction_test --disk_cache_path=$disk_cache_path"
|
|
"./build/test/kvcache_mem_insert_read_test --disk_cache_path=$disk_cache_path"
|
|
"./build/test/kvcache_save_load_test --disk_cache_path=$disk_cache_path"
|
|
)
|
|
|
|
|
|
# 遍历每个测试命令
|
|
for test in "${tests[@]}"; do
|
|
echo "Running: $test"
|
|
# 运行测试并捕获输出
|
|
output=$($test)
|
|
|
|
# 检查测试输出中是否包含 "Test Passed"
|
|
if echo "$output" | grep -q "Test Passed"; then
|
|
echo " Test Passed"
|
|
else
|
|
echo " Test Failed"
|
|
fi
|
|
|
|
sleep 1
|
|
done |