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
33 lines
739 B
Protocol Buffer
33 lines
739 B
Protocol Buffer
syntax = "proto3";
|
|
|
|
option go_package = "jd.com/jd-infer/xllm;xllm";
|
|
package xllm.proto;
|
|
|
|
message ModelCard {
|
|
// The model identifier, which can be referenced in the API endpoints.
|
|
optional string id = 1;
|
|
|
|
// The Unix timestamp (in seconds) when the model was created.
|
|
optional uint32 created = 2;
|
|
|
|
// the object type, which is always "model".
|
|
optional string object = 3;
|
|
|
|
// the organization that owns the model.
|
|
optional string owned_by = 4 [json_name = "owned_by"];
|
|
}
|
|
|
|
message ModelList {
|
|
optional string object = 1;
|
|
repeated ModelCard data = 2;
|
|
}
|
|
|
|
message ModelListRequest {
|
|
// The model identifier.
|
|
// string model = 1;
|
|
}
|
|
|
|
message ModelListResponse {
|
|
// The list of models.
|
|
repeated ModelCard data = 1;
|
|
} |