002f9879b2
Replaces cherry-picked upstream_ref with complete source trees. xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files) Complete: kernels → layers → models → runtime → scheduler → api Excluded: .git, binary images, third_party submodule checkouts ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files) Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops Excluded: tests, benchmarks, docs, examples (not needed for reference) Critical call chains now fully traceable: MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp Attention: ixformer.h → xllm_paged_attention → attention.cpp
42 lines
637 B
Protocol Buffer
42 lines
637 B
Protocol Buffer
syntax = "proto3";
|
|
|
|
option go_package = "jd.com/jd-infer/xllm;xllm";
|
|
package xllm.proto;
|
|
|
|
import "common.proto";
|
|
|
|
message RerankRequest {
|
|
string model = 1;
|
|
string query = 2;
|
|
repeated string documents = 3;
|
|
optional int32 top_n = 4;
|
|
optional int32 truncate_prompt_tokens = 5;
|
|
|
|
optional string user = 6;
|
|
|
|
optional string service_request_id = 7;
|
|
}
|
|
|
|
message RerankDocument {
|
|
string text = 1;
|
|
}
|
|
|
|
message RerankResult {
|
|
int32 index = 1;
|
|
|
|
RerankDocument document = 2;
|
|
|
|
float relevance_score = 3;
|
|
}
|
|
|
|
message RerankResponse {
|
|
string id = 1;
|
|
|
|
string model = 2;
|
|
|
|
Usage usage = 3;
|
|
|
|
repeated RerankResult results = 4;
|
|
}
|
|
|