Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
[Engine] SYCL: the prompt attention's query batch is 128 by default
Niko122109524eb479e0
diff --git a/sycl/src/prefill/prefill.cpp b/sycl/src/prefill/prefill.cppindex c08464219..20b04cd5f 100644--- a/sycl/src/prefill/prefill.cpp+++ b/sycl/src/prefill/prefill.cpp@@ -736,9 +736,9 @@ struct Prefill::Impl {float* attn_scratch = nullptr;int64_t attn_batch = [] { // SYCL port: how many queries the prompt path hands the FP32 attention kernel at onceconst char* v = std::getenv("STRATA_ATTN_BATCH"); // (the tensor-core kernel is opt-in and slower here)- const long long n = v ? std::atoll(v) : 32; // 32 was picked for a vector-matrix kernel; more queries- return (n >= 1 && n <= 1024) ? (int64_t) n : 32LL; // per launch give it more to overlap. Scratch grows too.- }(), cap = 0;+ const long long n = v ? std::atoll(v) : 128; // 32 was picked for a vector-matrix kernel; with the+ return (n >= 1 && n <= 1024) ? (int64_t) n : 128LL; // lane-cell score phase 128 reads a 4,106-token prompt+ }(), cap = 0; // 1.1% faster than 32 and a 16,380-token one 1.3%// MoEfloat *logits = nullptr, *w = nullptr, *GU = nullptr, *Dm = nullptr, *sgate = nullptr, *sup = nullptr,*shared = nullptr, *sg = nullptr;