apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 21 Packages Projects Releases Wiki Activity

[Optimization] Update Deepseekv3.2 model and dsa-indexer networking and add some unitest (#6762)

Browse Source 
* add deepseek model doc

* update deepseek model doc

* update deepseek model doc

* update deepseek model doc

* cwb suppor DSK_V32 Model

* update DSK_V32_DSA modeling

* Ibin Support DSK_DSA

* update kernel

* update yaml

* update requirements

* update pre_commit

* update model-runner

* fix CI bug

* del start.sh

* fix iluvatar_model_runner

* update DSA & add unitest

* update import deep_gemm
This commit is contained in:
AIbin
2026-03-11 15:52:54 +08:00
committed by GitHub
parent 97a4b3631e
commit 1118351b27
5 changed files with 884 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/gpu_ops/sparse_indexer/indexer_topk.cu
+3 -1
View File
@@ -75,7 +75,7 @@ void RadixTopkRaggedTransform(
unsigned int num_rows = input.dims()[0];
unsigned int max_len = input.dims()[1];
static cudaStream_t stream = input.stream();
cudaStream_t stream = input.stream();
cudaError_t status;
auto input_dtype = input.dtype();
@@ -129,6 +129,8 @@ void RadixTopkRaggedTransform(
max_len,
row_states_ptr,
stream);
} else {
PD_THROW("input_dtype should be one of [bf16, float]");
}
}