ZacharyZcR
cbd599024e
* Fuse CUDA expert MLP execution * Group CUDA expert transfers by device * Instrument grouped CUDA expert execution * Bound grouped CUDA decode scratch * Execute expert groups across GPUs in parallel * Release host backing for multi-GPU experts * Define quality-preserving memory policies * Overlap cold expert loading with resident compute * Adapt expert placement with session LFRU * Fuse q4 expert gate and up dispatch * Plan CPU work on physical cores * Batch grouped expert CUDA kernels * Separate VRAM and RAM expert placement * Add ragged multi-sequence decode forward * feat(runtime): add continuous decode scheduler * Route concurrent API requests through batch scheduler * Harden multiplex request lifecycle and framing * Cancel disconnected multiplex requests * Bind API port before starting the engine * fix automatic KV slot allocation * add native int4 Tensor Core grouped GEMM * add Tensor Core throughput benchmark * optimize packed int4 low-row kernels * add asynchronous CUDA staging streams * document validated six-GPU dense acceleration * tune six-GPU expert hot set * raise validated expert hot-set target * add CUDA MLA absorption core * fuse grouped expert gate and up projections * Warn for explicit lossy routing flags
28 lines
1007 B
C
28 lines
1007 B
C
#include <stdio.h>
|
|
#include "../tier.h"
|
|
|
|
static int fail(const char *message){
|
|
fprintf(stderr,"tier test failed: %s\n",message);
|
|
return 1;
|
|
}
|
|
|
|
int main(void){
|
|
uint32_t heat[6]={20,2,8,3,30,1};
|
|
int pinned[2]={0,1}, slot=-1, eid=-1; long gain=0;
|
|
if(!tier_pick_swap(heat,6,pinned,2,&slot,&eid,&gain)) return fail("hot expert not promoted");
|
|
if(slot!=1 || eid!=4 || gain!=28) return fail("wrong promotion candidate");
|
|
|
|
uint32_t stable[4]={20,18,24,4}; int resident[2]={0,1};
|
|
if(tier_pick_swap(stable,4,resident,2,&slot,&eid,&gain)) return fail("hysteresis did not block churn");
|
|
|
|
tier_decay(heat,6);
|
|
if(heat[0]!=10 || heat[1]!=1 || heat[4]!=15) return fail("heat decay");
|
|
|
|
uint32_t freq[5]={10,10,2,18,18}, last[5]={10,90,95,20,99};
|
|
int live[2]={0,1};
|
|
if(!tier_pick_lfru(freq,last,100,5,live,2,&slot,&eid,&gain)) return fail("LFRU promotion");
|
|
if(slot!=0||eid!=4) return fail("LFRU did not prefer recent ties");
|
|
puts("tier tests: ok");
|
|
return 0;
|
|
}
|