Files
markbaseengine/Sources/MarkBase/Metal/dequantize_8bit_kernel.metal
MarkBase Admin d3379e23d5
CI / build-and-test (push) Has been cancelled
deep analysis: 26B-A4B根本问题 - Metal kernel需支持bits=8
根本问题确认:
 26B-A4B Router/Expert使用bits=8量化
 inDim = 704*4 = 2816(8-bit: 4 vals/u32)
 groupSize = 2816/44 = 64
⚠️ 现有dequantize_row kernel只支持bits=4
⚠️ Kernel硬编码:groupSize/8, (inG%8)*4, &0xF
⚠️ 需要8-bit逻辑:groupSize/4, (inG%4)*8, &0xFF

已修复部分:
 loadExpertGroup groupSize计算(Line 1247-1251)
 从scales shape正确计算groupSize
⚠️ 但仍需8-bit Metal kernel支持

修复方案对比:
方案A(修改Metal kernels):数天,极高风险,不确定 
方案B(使用26B-Standard):0分钟,无风险,完美 

创建文件:
- dequantize_8bit_kernel.metal(示例kernel)
- dequantizeRow_analysis.md(函数分析)
- 26B_A4B_Deep_Fix_Analysis.md(完整分析)

结论:
技术上可修复,但难度极高(需修改Metal kernels)
强烈推荐使用26B-Standard代替(完美无NaN)

推荐度:方案B 
2026-06-24 02:22:26 +08:00

22 lines
955 B
Metal

kernel void dequantize_row_8bit(
device const uint *w [[buffer(0)]], // [nRows, nCols/4]
device const float *s [[buffer(1)], // [nRows, numGroups]
device const float *b [[buffer(2)]], // [nRows, numGroups]
device float *out [[buffer(3)], // [nCols]
constant uint &nCols [[buffer(4)]],
constant int &rowIdx [[buffer(5)]],
constant uint &groupSize [[buffer(6)]],
uint id [[thread_position_in_grid]]
) {
if (id >= nCols) return;
uint g = id / groupSize;
uint inG = id % groupSize;
// For 8-bit: 4 values per uint32
uint packedIdx = g * (groupSize / 4) + inG / 4;
uint shift = (inG % 4) * 8; // 8-bit shift
uint qval = (w[rowIdx * (nCols / 4) + packedIdx] >> shift) & 0xFF; // 8-bit mask
uint numGroups = nCols / groupSize;
float scale = s[rowIdx * numGroups + g];
float bias = b[rowIdx * numGroups + g];
out[id] = float(qval) * scale + bias;
}