Georgi GerganovandGitHub a70c8a0c4b kv-cache : use ggml_set_rows (#14285) ...

* kv-cache : use ggml_set_rows

ggml-ci

* graph : separate k and v indices

ggml-ci

* cont : remove redundant ifs

ggml-ci

* kv-cache : improve find_slot impl

* kv-cache : bounds-check when accessing slot_info indices

* kv-cache : add comments

ggml-ci

* ggml : add TODOs for adding GGML_OP_SET_ROWS support in the backends

ggml-ci

2025-07-03 10:53:35 +03:00

..

dpct

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

backend.hpp

sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs (#12858)

2025-05-09 16:34:08 +01:00

binbcast.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

binbcast.hpp

SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975)

2025-04-18 15:57:56 +02:00

CMakeLists.txt

SYCL: Bump oneMath commit (#14152)

2025-06-13 08:45:37 +01:00

common.cpp

SYCL: Remove misleading ggml_sycl_op_flatten function (#12387)

2025-03-31 11:25:24 +02:00

common.hpp

sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973)

2025-06-25 18:09:55 +02:00

concat.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

concat.hpp

SYCL: Refactor ggml_sycl_compute_forward (#11121)

2025-01-10 08:13:03 +08:00

conv.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

conv.hpp

SYCL: Refactor ggml_sycl_compute_forward (#11121)

2025-01-10 08:13:03 +08:00

convert.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

convert.hpp

sycl: addressing non-contiguous src1 mul_mats (nc and batched) (#13343)

2025-05-08 10:08:01 +01:00

cpy.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

cpy.hpp

SYCL: Move CPY kernels to a separate file and add few missing kernels (#12133)

2025-03-03 11:07:22 +01:00

dequantize.hpp

sycl: Add reorder to Q6_K mmvq implementation (#13885)

2025-06-09 11:47:07 +02:00

dmmv.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

dmmv.hpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

element_wise.cpp

ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)

2025-06-29 11:04:10 +02:00

element_wise.hpp

ggml : implement REGLU/GEGLU/SWIGLU ops (#14158)

2025-06-29 11:04:10 +02:00

gemm.hpp

sycl: Remove not needed copy f16->f32 for dnnl mul mat (#14125)

2025-06-12 15:15:11 +02:00

getrows.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

getrows.hpp

SYCL: Remove misleading ggml_sycl_op_flatten function (#12387)

2025-03-31 11:25:24 +02:00

ggml-sycl.cpp

kv-cache : use ggml_set_rows (#14285)

2025-07-03 10:53:35 +03:00

gla.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

gla.hpp

SYCL: Add gated linear attention kernel (#11175)

2025-01-15 11:20:17 +08:00

im2col.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

im2col.hpp

SYCL: Remove misleading ggml_sycl_op_flatten function (#12387)

2025-03-31 11:25:24 +02:00

mmq.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

mmq.hpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

mmvq.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

mmvq.hpp

llama : reorganize source code + improve CMake (#8006)

2024-06-26 18:33:02 +03:00

norm.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

norm.hpp

SYCL: Remove misleading ggml_sycl_op_flatten function (#12387)

2025-03-31 11:25:24 +02:00

outprod.cpp

sycl: Add more debug prints (#13640)

2025-05-26 10:28:53 +02:00

outprod.hpp

SYCL: Refactor ggml_sycl_compute_forward (#11121)

2025-01-10 08:13:03 +08:00

presets.hpp

Optimize RWKV6 Operator Naming and Implement Multi-core CPU/ SYCL Acceleration (#10133)

2024-11-07 15:19:10 +08:00

quants.hpp

sycl: Add reorder to Q6_K mmvq implementation (#13885)

2025-06-09 11:47:07 +02:00

rope.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

rope.hpp

SYCL: Add non-contiguous support in ROPE (#12993)

2025-04-21 19:13:30 +05:30

softmax.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

softmax.hpp

SYCL : SOFTMAX F16 mask support and other fixes (#11261)

2025-01-28 09:56:58 +00:00

sycl_hw.cpp

sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973)

2025-06-25 18:09:55 +02:00

sycl_hw.hpp

sycl: GGML_SYCL_DISABLE_OPT on by default for all Intel Devices (#13973)

2025-06-25 18:09:55 +02:00

tsembd.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

tsembd.hpp

SYCL: Refactor ggml_sycl_compute_forward (#11121)

2025-01-10 08:13:03 +08:00

vecdotq.hpp

sycl: Add reorder to Q6_K mmvq implementation (#13885)

2025-06-09 11:47:07 +02:00

wkv.cpp

sycl: add usage of enqueue_functions extension (#14244)

2025-06-20 15:07:21 +02:00

wkv.hpp

llama: Add support for RWKV v7 architecture (#12412)

2025-03-18 07:27:50 +08:00