CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
c22473b580807929fd9e3a3344a48e8cfbe6c88f
llama.cpp/ggml/src/ggml-cuda
History
JJJYmmm d261223d24 model: add support for qwen3vl series (#16780) 
* support qwen3vl series.

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>

* bugfix: fix the arch check for qwen3vl-moe.

* use build_ffn

* optimize deepstack structure

* optimize deepstack feature saving

* Revert "optimize deepstack feature saving" for temporal fix

This reverts commit f321b9fdf1.

* code clean

* use fused qkv in clip

* clean up / rm is_deepstack_layers for simplification

* add test model

* move test model to "big" section

* fix imrope check

* remove trailing whitespace

* fix rope fail

* metal : add imrope support

* add imrope support for sycl

* vulkan: add imrope w/o check

* fix vulkan

* webgpu: add imrope w/o check

* Update gguf-py/gguf/tensor_mapping.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix tensor mapping

---------

Co-authored-by: Thireus ☠ <Thireus@users.noreply.github.com>
Co-authored-by: yairpatch <yairpatch@users.noreply.github.com>
Co-authored-by: LETS-BEE <LETS-BEE@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2025-10-30 16:19:14 +01:00
..
template-instances
CUDA: faster tile FA, add oob checks, more HSs (#16492)
2025-10-11 20:54:32 +02:00
vendors
HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.0 (#16221)
2025-10-01 23:09:25 +02:00
acc.cu
llama/ggml: add LLM training support (#10544)
2025-05-12 14:44:49 +02:00
acc.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
add-id.cu
musa: fix build warnings (#15258)
2025-08-20 10:17:37 +08:00
add-id.cuh
llama : add gpt-oss (#15091)
2025-08-05 22:10:36 +03:00
arange.cu
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
arange.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
argmax.cu
cuda : optimize argmax (#10441)
2024-11-21 18:18:50 +01:00
argmax.cuh
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
2024-10-03 21:17:26 +03:00
argsort.cu
cuda : fix argsort with 64k+ rows (#16849)
2025-10-30 08:56:28 +01:00
argsort.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
binbcast.cu
ggml: fix CUDA grid launch condition for large block_nums.y in binbcast (#16742)
2025-10-24 21:39:37 +02:00
binbcast.cuh
CUDA: fuse adds, fuse add with rms norm (#15631)
2025-08-29 11:35:58 +08:00
clamp.cu
cuda: unary ops as float + de-duplicate (ggml/1130)
2025-03-03 18:18:11 +02:00
clamp.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
CMakeLists.txt
CUDA: faster tile FA, add oob checks, more HSs (#16492)
2025-10-11 20:54:32 +02:00
common.cuh
CUDA: use fastdiv in set-rows (#16834)
2025-10-29 21:11:53 +08:00
concat.cu
musa: fix all warnings, re-enable -DLLAMA_FATAL_WARNINGS=ON in ci and update doc (#12611)
2025-03-30 10:59:38 +02:00
concat.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
conv2d-dw.cu
CUDA: add conv_2d_dw (#14265)
2025-06-20 09:50:24 +08:00
conv2d-dw.cuh
CUDA: add conv_2d_dw (#14265)
2025-06-20 09:50:24 +08:00
conv2d-transpose.cu
CUDA: add conv_2d_transpose (#14287)
2025-06-20 22:48:24 +08:00
conv2d-transpose.cuh
CUDA: add conv_2d_transpose (#14287)
2025-06-20 22:48:24 +08:00
conv2d.cu
CUDA: fix build error from ambiguous __half conversions in conv2d (#15690)
2025-09-01 06:55:06 +05:30
conv2d.cuh
CUDA: add conv2d (#15635)
2025-08-28 20:33:03 +02:00
conv-transpose-1d.cu
musa: add GGML_UNUSED_VARS (#15446)
2025-08-21 11:06:05 +08:00
conv-transpose-1d.cuh
feat: cuda implementation for ggml_conv_transpose_1d (ggml/854)
2024-07-08 12:23:00 +03:00
convert.cu
musa: add GGML_UNUSED_VARS (#15446)
2025-08-21 11:06:05 +08:00
convert.cuh
CUDA: General GEMV fusion (#16715)
2025-10-26 19:28:04 +08:00
count-equal.cu
ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL operator when ‘ne’ is small (#10213)
2024-11-09 08:35:46 +01:00
count-equal.cuh
ggml/ex: calculate accuracy in graph, adapt MNIST (ggml/980)
2024-10-03 21:17:26 +03:00
cp-async.cuh
CUDA: FA support for Deepseek (Ampere or newer) (#13306)
2025-05-09 13:34:58 +02:00
cpy-utils.cuh
HIP: Cleanup hipification header (#15285)
2025-08-14 16:23:56 +02:00
cpy.cu
cuda : use fast copy when src and dst are of different type and contiguous (#16789)
2025-10-26 21:31:41 +01:00
cpy.cuh
cuda : remove legacy copy-op pointer indirection code (#16485)
2025-10-14 11:53:49 +02:00
cross-entropy-loss.cu
CUDA: add dynamic shared mem to softmax, refactor general usage (#14497)
2025-07-03 07:45:11 +08:00
cross-entropy-loss.cuh
ggml/examples: add backend support for numerical optimization (ggml/949)
2024-09-20 21:15:05 +03:00
dequantize.cuh
CUDA: replace GGML_CUDA_F16 with CUDA arch checks (#15433)
2025-08-20 16:58:49 +02:00
diagmask.cu
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
diagmask.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
fattn-common.cuh
CUDA: better error for FA kernel with 0 occupancy (#16643)
2025-10-21 15:27:53 +02:00
fattn-mma-f16.cuh
musa: add GGML_UNUSED_VARS (#15446)
2025-08-21 11:06:05 +08:00
fattn-tile.cu
CUDA: faster tile FA, add oob checks, more HSs (#16492)
2025-10-11 20:54:32 +02:00
fattn-tile.cuh
CUDA: fix numerical issues in tile FA kernel (#16540)
2025-10-13 17:29:45 +03:00
fattn-vec.cuh
CUDA: enable FA for FP32 KV cache (#16546)
2025-10-14 14:22:47 +02:00
fattn-wmma-f16.cu
HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.0 (#16221)
2025-10-01 23:09:25 +02:00
fattn-wmma-f16.cuh
CUDA: faster tile FA, add oob checks, more HSs (#16492)
2025-10-11 20:54:32 +02:00
fattn.cu
CUDA: enable FA for FP32 KV cache (#16546)
2025-10-14 14:22:47 +02:00
fattn.cuh
CUDA: refactor FA support/selection code (#15454)
2025-08-20 23:14:14 +02:00
getrows.cu
CUDA: fix GET_ROWS for large tensors (#15882)
2025-09-09 08:11:01 +02:00
getrows.cuh
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (#13199)
2025-04-30 23:12:59 +02:00
ggml-cuda.cu
CUDA: Fix bug in topk-moe for gpt-oss (#16821)
2025-10-29 15:55:06 +08:00
gla.cu
llama: add support for QRWKV6 model architecture (#11001)
2025-01-10 09:58:08 +08:00
gla.cuh
llama: add support for QRWKV6 model architecture (#11001)
2025-01-10 09:58:08 +08:00
im2col.cu
CUDA: fix im2col_3d to respect non-contiguous inputs (views) (#15956)
2025-09-16 00:28:31 +02:00
im2col.cuh
ggml: add ops for WAN video model (cuda && cpu) (#15669)
2025-09-04 10:38:49 +02:00
mean.cu
cuda : fix GGML_CUDA_GRAPHS=OFF (#15300)
2025-08-14 13:22:07 +03:00
mean.cuh
CUDA: add mean operation (#14313)
2025-06-22 12:39:54 +08:00
mma.cuh
CUDA: Add mul_mat_id support for the mmf kernel (#15767)
2025-09-09 14:38:02 +08:00
mmf.cu
CUDA: add fp kernel for larger batch size MoE (#16512)
2025-10-14 13:15:15 +02:00
mmf.cuh
CUDA: add fp kernel for larger batch size MoE (#16512)
2025-10-14 13:15:15 +02:00
mmid.cu
CUDA: add fp kernel for larger batch size MoE (#16512)
2025-10-14 13:15:15 +02:00
mmid.cuh
CUDA: add fp kernel for larger batch size MoE (#16512)
2025-10-14 13:15:15 +02:00
mmq.cu
CUDA: add fp kernel for larger batch size MoE (#16512)
2025-10-14 13:15:15 +02:00
mmq.cuh
CUDA: MoE helper in device code, better tile sizes (#15525)
2025-08-25 17:23:40 +02:00
mmvf.cu
CUDA: add unused vars to mmvf and mmvq (#16807)
2025-10-28 10:31:21 +08:00
mmvf.cuh
CUDA: General GEMV fusion (#16715)
2025-10-26 19:28:04 +08:00
mmvq.cu
Hide latency of bias and gate-loading (#16847)
2025-10-30 11:34:15 +08:00
mmvq.cuh
CUDA: General GEMV fusion (#16715)
2025-10-26 19:28:04 +08:00
norm.cu
CUDA: Optimize rms_norm_f32 kernel and its fused variants, giving 1-6% perf E2E (#15715)
2025-09-03 19:59:16 +02:00
norm.cuh
CUDA: fuse adds, fuse add with rms norm (#15631)
2025-08-29 11:35:58 +08:00
opt-step-adamw.cu
ggml: new optimization interface (ggml/988)
2024-11-17 08:30:29 +02:00
opt-step-adamw.cuh
ggml/examples: add backend support for numerical optimization (ggml/949)
2024-09-20 21:15:05 +03:00
opt-step-sgd.cu
finetune: SGD optimizer, more CLI args (#13873)
2025-08-14 12:03:57 +02:00
opt-step-sgd.cuh
finetune: SGD optimizer, more CLI args (#13873)
2025-08-14 12:03:57 +02:00
out-prod.cu
CPU/CUDA: fix (GQA) mul mat back, add CUDA support (#11380)
2025-01-24 12:38:31 +01:00
out-prod.cuh
ggml/examples: add backend support for numerical optimization (ggml/949)
2024-09-20 21:15:05 +03:00
pad_reflect_1d.cu
musa: fix build warnings (#15611)
2025-09-26 02:56:10 +02:00
pad_reflect_1d.cuh
cuda : add Pad Reflect 1D support (#14659)
2025-08-22 13:06:29 +02:00
pad.cu
ggml: add ops for WAN video model (cuda && cpu) (#15669)
2025-09-04 10:38:49 +02:00
pad.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
pool2d.cu
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
pool2d.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
quantize.cu
CUDA: fastdiv, launch bounds for mmvq + q8_1 quant (#15802)
2025-09-05 16:07:02 +02:00
quantize.cuh
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (#13199)
2025-04-30 23:12:59 +02:00
reduce_rows.cuh
musa: fix build warnings (#15258)
2025-08-20 10:17:37 +08:00
roll.cu
CUDA: add roll (#14919)
2025-07-29 14:45:18 +08:00
roll.cuh
CUDA: add roll (#14919)
2025-07-29 14:45:18 +08:00
rope.cu
model: add support for qwen3vl series (#16780)
2025-10-30 16:19:14 +01:00
rope.cuh
RoPE: fix back, CUDA support for back + noncont. (#11240)
2025-01-15 12:51:37 +01:00
scale.cu
ggml: add ops for WAN video model (cuda && cpu) (#15669)
2025-09-04 10:38:49 +02:00
scale.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
set-rows.cu
CUDA: use fastdiv in set-rows (#16834)
2025-10-29 21:11:53 +08:00
set-rows.cuh
CUDA: add set rows for f32 and f16 (#14551)
2025-07-12 16:31:38 +03:00
set.cu
cuda: add SET operation support (#16804)
2025-10-28 20:10:28 +01:00
set.cuh
cuda: add SET operation support (#16804)
2025-10-28 20:10:28 +01:00
softcap.cu
cuda : add softcap fusion (#14907)
2025-07-29 14:22:03 +02:00
softcap.cuh
cuda : add softcap fusion (#14907)
2025-07-29 14:22:03 +02:00
softmax.cu
llama : add gpt-oss (#15091)
2025-08-05 22:10:36 +03:00
softmax.cuh
CUDA: backwards pass for misc. ops, add tests (#11257)
2025-01-16 16:43:38 +01:00
ssm-conv.cu
model : support LiquidAI LFM2 hybrid family (#14620)
2025-07-11 20:27:01 +02:00
ssm-conv.cuh
ggml : faster ssm scan (#10558)
2025-03-31 18:05:13 +02:00
ssm-scan.cu
ggml : fix SSM_SCAN for n_groups > 1 (#15625)
2025-08-28 10:11:36 -04:00
ssm-scan.cuh
ggml : faster ssm scan (#10558)
2025-03-31 18:05:13 +02:00
sum.cu
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n (#15132)
2025-08-13 10:04:46 +02:00
sum.cuh
tests: add gradient tests for all backends (ggml/932)
2024-09-08 11:05:55 +03:00
sumrows.cu
CUDA: Optimize reduce_rows_f32 kernel, leading up to 25x perf improvement on kernel-level and 10% perf increase for Gemma3n (#15132)
2025-08-13 10:04:46 +02:00
sumrows.cuh
CUDA: add mean operation (#14313)
2025-06-22 12:39:54 +08:00
topk-moe.cu
CUDA: support for weight clamp in top-k norm (#16702)
2025-10-27 09:06:16 +08:00
topk-moe.cuh
CUDA: support for weight clamp in top-k norm (#16702)
2025-10-27 09:06:16 +08:00
tsembd.cu
ggml : fix padding in timestep embedding kernels (#15932)
2025-09-16 15:25:57 +02:00
tsembd.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
unary.cu
CUDA: General GEMV fusion (#16715)
2025-10-26 19:28:04 +08:00
unary.cuh
CUDA: General GEMV fusion (#16715)
2025-10-26 19:28:04 +08:00
upscale.cu
ggml : fix interpolate with align-corners and ne=1 (#16700)
2025-10-27 21:50:22 +01:00
upscale.cuh
llama : reorganize source code + improve CMake (#8006)
2024-06-26 18:33:02 +03:00
vecdotq.cuh
CUDA: Accelerate MXFP4 table lookup using __byte_perm (#15451)
2025-08-25 23:21:22 +02:00
wkv.cu
llama: Add support for RWKV v7 architecture (#12412)
2025-03-18 07:27:50 +08:00
wkv.cuh
llama: Add support for RWKV v7 architecture (#12412)
2025-03-18 07:27:50 +08:00