llama.cpp/ggml/src at b9970 - llama.cpp - Gitea: Git with a cup of tea

upstream-archive/llama.cpp

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-25 20:21:03 -05:00

Files

History

fairydreaming 00f5442cc4 ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231 )

* ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer

* ggml : remove scale parameters from lightning indexer OP, add f16 mask parameter

* tests : add GGML_OP_LIGHTNING_INDEXER tests

* ggml : bump RPC version

* chore : check if lightning indexer input tensors are not transposed

* tests : count flops instead of bandwidth in lightning indexer test

* chore : add missing const

* chore : whitespace

* ggml : renamed variables in CPU lightning indexer implementation

* ggml : fix lightning indexer mask broadcasting

* tests : tests for lightning indexer mask broadcasting

* chore : whitespace

* llama : use GGML_OP_LIGHTNING_INDEXER in DeepSeek V3.2 and DeepSeek V4 models

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>

2026-07-11 11:39:07 +02:00

..

vulkan: add get/set tensor 2d functions (#22514 )

2026-04-30 17:37:13 +02:00

vulkan: add get/set tensor 2d functions (#22514 )

2026-04-30 17:37:13 +02:00

ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231 )

2026-07-11 11:39:07 +02:00

ggml : process data in smaller chunks in CUDA ggml_top_k() and ggml_argsort() to reduce temporary buffers memory usage (#24776 )

2026-07-09 20:07:12 +02:00

ggml-et: Initial ET backend (#24179 )

2026-07-10 12:38:34 +08:00

hexagon: improve ARGSORT performance for small tensors (#25512 )

2026-07-10 09:06:06 -07:00

ggml-hip: enable -funsafe-math-optimizations (#24668 )

2026-07-09 11:02:26 +03:00

metal : add CONV_2D_DW (depthwise convolution) support (#21565 )

2026-07-09 12:29:15 +03:00

ggml-cuda: native bf16 flash attention for vec kernel (#20525 )

2026-03-22 11:05:51 +01:00

opencl: add int8 dp4 dense and MoE prefill optimization for Adreno GPUs (#25537 )

2026-07-10 23:05:58 -07:00

[CUDA] Added a cudaMemcpy2DAsync fast path to ggml_cuda_cpy (#25057 )

2026-06-27 17:46:21 +05:30

rpc : keep last_graph_uid in the device context (#23273 )

2026-05-19 09:42:36 +03:00

[SYCL] fix unsupported UT cases of CONT & CPY (#25231 )

2026-07-07 12:20:52 +03:00

ggml-virtgpu : include missing mutex header (#22810 )

2026-05-10 17:32:41 +02:00

Vulkan: route large matmuls to medium tile on Adreno (#24877 )

2026-07-11 10:28:29 +02:00

ggml-webgpu: tune subgroup split (d_split) in flash_attn_vec (#25418 )

2026-07-09 08:34:19 +09:00

vulkan: add get/set tensor 2d functions (#22514 )

2026-04-30 17:37:13 +02:00

ggml-zendnn : fixed naming of matmul function (#20964 )

2026-05-27 00:59:35 +02:00

CMakeLists.txt

ggml-et: Initial ET backend (#24179 )

2026-07-10 12:38:34 +08:00

ggml-alloc.c

ggml-alloc: fix out-of-bounds read in ggml_dyn_tallocr_remove_block (ggml/1492)

2026-05-25 12:38:01 +03:00

ggml-backend-dl.cpp

hexagon: enable offloading to Hexagon on Windows on Snapdragon (#19150 )

2026-01-29 12:33:21 -08:00

ggml-backend-dl.h

hexagon: enable offloading to Hexagon on Windows on Snapdragon (#19150 )

2026-01-29 12:33:21 -08:00

ggml-backend-impl.h

ggml: backend-agnostic tensor parallelism (experimental) (#19378 )

2026-04-09 16:42:19 +02:00

ggml-backend-meta.cpp

abort if we see a multi buffer (#25276 )

2026-07-05 20:38:47 +02:00

ggml-backend-reg.cpp

ggml-et: Initial ET backend (#24179 )

2026-07-10 12:38:34 +08:00

ggml-backend.cpp

Revert "sched : reintroduce less synchronizations during split compute (#20793 )" (#25138 )

2026-06-30 08:41:45 +08:00

ggml-common.h

Add Q2_0 quantization: type definition and CPU backend (#24448 )

2026-07-07 12:05:47 -07:00

ggml-impl.h

ggml: add graph_reused (#21764 )

2026-04-16 17:21:28 +08:00

ggml-opt.cpp

fix: free ctx_copy in ggml_opt_free to plug per-training-session leak (#21592 )

2026-04-08 17:40:15 +02:00

ggml-quants.c

Add Q2_0 quantization: type definition and CPU backend (#24448 )

2026-07-07 12:05:47 -07:00

ggml-quants.h

Add Q2_0 quantization: type definition and CPU backend (#24448 )

2026-07-07 12:05:47 -07:00

ggml-threading.cpp

ggml : build backends as libraries (#10256 )

2024-11-14 18:04:35 +01:00

ggml-threading.h

remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797 )

2024-12-12 19:02:49 +01:00

ggml.c

ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231 )

2026-07-11 11:39:07 +02:00

ggml.cpp

ggml : Print backtrace on uncaught C++ exceptions (ggml/1232)

2025-06-01 13:43:57 +03:00

gguf.cpp

ggml: gguf_init_from_callback and gguf_init_from_buffer (#22341 )

2026-05-25 11:33:29 +02:00