mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

[SYCL] Support gpt-oss by OPs add-id, mul_mat for mxfp4, swiglu_oai (#17826)

Browse Source 
* support gpt-oss GPU by OP add-id, mul_mat for mxfp4, swiglu_oai, fix warning

* fix fault ut case, update ops.md

* rebase, fix format issue
This commit is contained in:
Neo Zhang Jianyu
2025-12-15 10:35:15 +08:00
committed by GitHub
parent 745fa0e78b
commit 4aced7a631
15 changed files with 1201 additions and 385 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/ssm_conv.cpp
+1 -1
View File
@@ -88,7 +88,7 @@ void ggml_sycl_ssm_conv(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_ASSERT(src0->nb[0] == sizeof(float));
GGML_ASSERT(src1->nb[0] == sizeof(float));
GGML_ASSERT(src0->nb[1] == src0->ne[0] * static_cast<int>(sizeof(float)));
GGML_ASSERT(src0->nb[1] == src0->ne[0] * sizeof(float));
const int src_stride_inner = ncs;
const int src_stride_seq = ncs * d_inner;