mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 31 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/convert.cpp
+15
View File
@@ -472,6 +472,16 @@ static void dequantize_row_iq4_nl_sycl(const void *vx, dst_t *y, const int64_t k
}
}
template <typename dst_t>
static void dequantize_row_mxfp4_sycl(const void * vx, dst_t * y, const int64_t k, dpct::queue_ptr stream) {
const int nb = (k + QK_K - 1) / QK_K;
stream->parallel_for(
sycl::nd_range<3>(sycl::range<3>(1, 1, nb) * sycl::range<3>(1, 1, 32), sycl::range<3>(1, 1, 32)),
[=](sycl::nd_item<3> item_ct1) {
dequantize_block_mxfp4(vx, y, item_ct1);
});
}
template <typename src_t, typename dst_t>
static void convert_unary_nc(const void * __restrict__ vx, dst_t * __restrict__ y, const int64_t ne00, const int64_t ne01,
const int64_t ne02, const int64_t s01, const int64_t s02, const int64_t s03,
@@ -518,6 +528,7 @@ static void convert_unary_sycl(const void * vx, dst_t * y, const int64_t k, dpct
convert_unary_nc_sycl<src_t>(vx, y, k, 1, 1, 1, k, k, k, queue);
}
to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type, ggml_tensor * dst) {
switch (type) {
case GGML_TYPE_Q4_0:
@@ -571,6 +582,8 @@ to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type, ggml_tensor * dst) {
return dequantize_row_iq4_xs_sycl;
case GGML_TYPE_IQ4_NL:
return dequantize_row_iq4_nl_sycl;
case GGML_TYPE_MXFP4:
return dequantize_row_mxfp4_sycl;
case GGML_TYPE_F32:
return convert_unary_sycl<float>;
#ifdef GGML_SYCL_HAS_BF16
@@ -636,6 +649,8 @@ to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type, ggml_tensor *dst) {
return dequantize_row_iq4_xs_sycl;
case GGML_TYPE_IQ4_NL:
return dequantize_row_iq4_nl_sycl;
case GGML_TYPE_MXFP4:
return dequantize_row_mxfp4_sycl;
case GGML_TYPE_F16:
return convert_unary_sycl<sycl::half>;
#ifdef GGML_SYCL_HAS_BF16