Gahow Wang
9f1fbbb98b
Store expert gate_up_proj and down_proj weights in FP8 E4M3 (1 byte/elem) with per-expert FP32 scale factors. At inference, a fused CUDA kernel dequantizes to BF16 before the existing cuBLAS batched GEMM. Results on gpt-oss-20b (50-problem GSM8K subset): - FP8 TP=1: 47/50 = 94.0% (single RTX 5090, ~25 GB VRAM) - BF16 TP=2: 47/50 = 94.0% (requires 2× RTX 5090, ~39 GB total) No measurable accuracy degradation. Model size: 41.8 GB → 22.7 GB (−46%). New files: - tools/quantize_fp8.py: offline BF16→FP8 conversion script - csrc/quantization/dequant_fp8.cu: per-expert-scale dequant kernel - crates/xserv-kernels/src/quantization.rs: Rust FFI wrapper - tools/eval_gsm8k_batch.sh: GSM8K accuracy evaluation harness Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
52 lines
1.4 KiB
Plaintext
52 lines
1.4 KiB
Plaintext
#include <cuda_bf16.h>
|
|
#include <cuda_fp8.h>
|
|
#include "../common.cuh"
|
|
|
|
// Dequantize FP8 E4M3 → BF16 with per-expert (per-batch-slice) FP32 scale.
|
|
//
|
|
// Input: src [num_experts, rows, cols] FP8 E4M3 (1 byte each)
|
|
// scales [num_experts] FP32
|
|
// Output: dst [num_experts, rows, cols] BF16
|
|
//
|
|
// Each element: dst[e, r, c] = bf16( float(src[e, r, c]) * scales[e] )
|
|
|
|
__global__ void dequant_fp8e4m3_to_bf16_kernel(
|
|
const __nv_fp8_e4m3* __restrict__ src,
|
|
const float* __restrict__ scales,
|
|
__nv_bfloat16* __restrict__ dst,
|
|
int num_experts, int rows, int cols
|
|
) {
|
|
int idx = blockIdx.x * blockDim.x + threadIdx.x;
|
|
int total = num_experts * rows * cols;
|
|
if (idx >= total) return;
|
|
|
|
int expert_stride = rows * cols;
|
|
int expert = idx / expert_stride;
|
|
float scale = scales[expert];
|
|
float val = float(src[idx]) * scale;
|
|
dst[idx] = __float2bfloat16(val);
|
|
}
|
|
|
|
extern "C" {
|
|
|
|
void launch_dequant_fp8e4m3_to_bf16(
|
|
const void* src,
|
|
const void* scales,
|
|
void* dst,
|
|
int num_experts, int rows, int cols,
|
|
void* stream
|
|
) {
|
|
int total = num_experts * rows * cols;
|
|
int block = 256;
|
|
int grid = (total + block - 1) / block;
|
|
dequant_fp8e4m3_to_bf16_kernel<<<grid, block, 0, (cudaStream_t)stream>>>(
|
|
(const __nv_fp8_e4m3*)src,
|
|
(const float*)scales,
|
|
(__nv_bfloat16*)dst,
|
|
num_experts, rows, cols
|
|
);
|
|
CUDA_CHECK_LAST_ERROR();
|
|
}
|
|
|
|
}
|