tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : add gpt-oss (#15091)

Browse Source 
* oai moe

* compat with new checkpoint

* add attn sink impl

* add rope scaling yarn

* logits match with latest transformers code

* wip chat template

* rm trailing space

* use ggml_scale_bias

* rm redundant is_swa_all

* convert interleaved gate_up

* graph : fix activation function to match reference (#7)

* vocab : handle o200k_harmony special tokens

* ggml : add attention sinks support (#1)

* llama : add attn sinks

* ggml : add attn sinks

* cuda : add attn sinks

* vulkan : add support for sinks in softmax

remove unnecessary return

* ggml : add fused swiglu_oai op (#11)

* ggml : add fused swiglu_oai op

* Update ggml/src/ggml-cpu/ops.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* update CUDA impl

* cont : metal impl

* add vulkan impl

* test-backend-ops : more test cases, clean up

* llama : remove unfused impl

* remove extra lines

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>

* repack mxfp4 upon conversion

* clean up a bit

* enable thinking

* add quick hack to render only some special tokens

* fix bf16 conversion

* remove vocab hack

* webui ok

* support chat parsing for gpt-oss

* fix webui

* direct mapping mxfp4, FINALLY

* force using mxfp4

* properly use lazy tensor

* ggml : add mxfp4

ggml : use e8m0 conversion instead of powf

Co-authored-by: Diego Devesa <slarengh@gmail.com>

change kvalues_mxfp4 table to match e2m1 (#6)

metal : remove quantization for now (not used)

cuda : fix disabled CUDA graphs due to ffn moe bias

vulkan : add support for mxfp4

cont : add cm2 dequant

* ggml : add ggml_add_id (#13)

* ggml : add ggml_add_id

* add cuda impl

* llama : add weight support check for add_id

* perf opt

* add vulkan impl

* rename cuda files

* add metal impl

* allow in-place ggml_add_id

* llama : keep biases on CPU with --cpu-moe

* llama : fix compile error

ggml-ci

* cuda : add fallback for __nv_cvt_e8m0_to_bf16raw

ggml-ci

* cleanup

ggml-ci

* sycl : fix supports_op for MXFP4

ggml-ci

* fix Unknown reasoning format

* ggml-cpu : fix AVX build

ggml-ci

* fix hip build

ggml-ci

* cuda : add mxfp4 dequantization support for cuBLAS

ggml-ci

* ggml-cpu : fix mxfp4 fallback definitions for some architectures

ggml-ci

* cuda : fix version required for __nv_cvt_e8m0_to_bf16raw

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov
2025-08-05 22:10:36 +03:00
committed by GitHub
parent f324a3b715
commit fd1234cb46
83 changed files with 2942 additions and 227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
ggml/src/ggml-sycl/ggml-sycl.cpp
View File

@@ -4193,15 +4193,9 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
case GGML_OP_MUL_MAT:
case GGML_OP_MUL_MAT_ID:
{
struct ggml_tensor * a;
struct ggml_tensor * b;
if (op->op == GGML_OP_MUL_MAT) {
a = op->src[0];
b = op->src[1];
} else {
a = op->src[2];
b = op->src[1];
}
struct ggml_tensor * a = op->src[0];
struct ggml_tensor * b = op->src[1];
if (a->ne[3] != b->ne[3]) {
return false;
}
@@ -4216,7 +4210,9 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
}
}
ggml_type src0_type = op->src[0]->type;
if (src0_type == GGML_TYPE_BF16) {
if (src0_type == GGML_TYPE_BF16 || src0_type == GGML_TYPE_MXFP4) {
// TODO: support MXFP4
// FIXME: keep a list of supported types to avoid breaking the backend when a new type is added
return false;
}
return true;
@@ -4361,6 +4357,10 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
if (op->src[0]->ne[3] != 1) {
return false;
}
// TODO: support attention sinks [TAG_ATTN_SINKS]
if (op->src[2]) {
return false;
}
// TODO: support broadcast
// ref: https://github.com/ggml-org/llama.cpp/pull/14435
return !op->src[1] || (op->src[1]->ne[2] == 1 && op->src[1]->ne[3] == 1);