Georgi GerganovandJohannes Gäßler 225e7a1438 llama : add high-throughput mode (#14363) ...

* kv-cache : prepare K/V buffers for separation

ggml-ci

* batched-bench : fix oob write

ggml-ci

* llama : add "virtual sequences"

ggml-ci

* llama : use "stream" vs "virtual sequence"

ggml-ci

* graph : fix stream splitting when KV cache is not used

ggml-ci

* kv-cache : add multi-stream save/load support

ggml-ci

* llama : add "--attn-streams" flag

ggml-ci

* kv-cache : fix handling when find_slot fails

ggml-ci

* kv-cache : restore find_slot impl

ggml-ci

* kv-cache : add comments

* kv-cache : add bounds checks for sequence id

ggml-ci

* cont : add n_seq_max to batch allocr

ggml-ci

* kv-cache : perform stream copies lazily after llama_synchronize

ggml-ci

* kv-cache : avoid throwing exceptions across the C boundary

ggml-ci

* CUDA: 4D FlashAttention support (#14628)

* CUDA: 4D FlashAttention support

* CUDA: fix WMMA FA kernel

* llama : rename attn_streams -> kv_unified

ggml-ci

* common : rename kv_split -> kv_unified

ggml-ci

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

2025-07-16 16:35:42 +03:00

..

ggml-blas

cmake : Fix broken CMake error messages (ggml/1252)

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

ggml-cann

ggml : add build-time message to remind about ggml_set_rows (#14661)

2025-07-13 10:36:33 +03:00

ggml-cpu

ggml : add asserts (#14720)

2025-07-16 14:43:32 +03:00

ggml-cuda

llama : add high-throughput mode (#14363)

2025-07-16 16:35:42 +03:00

ggml-hip

HIP: disable rocwmma on gfx12 by default until rocm 7.0 (#14202)

2025-06-16 13:47:38 +02:00

ggml-metal

metal : Add missing unary ops Metal support (#14660)

2025-07-13 08:38:13 +03:00

ggml-musa

musa: enable fp16 mma (all) and cublas on qy2 (#13842)

2025-06-26 12:11:59 +08:00

ggml-opencl

ggml : add build-time message to remind about ggml_set_rows (#14661)

2025-07-13 10:36:33 +03:00

ggml-rpc

rpc : nicer error messages for RPC server crash (#14076)

2025-06-10 09:41:01 +03:00

ggml-sycl

sycl: Hotfix for non dnnl codepath (#14677)

2025-07-14 18:12:42 +01:00

ggml-vulkan

vulkan: fix noncontig check for mat_mul_id splitting (#14683)

2025-07-15 21:51:09 +02:00

CMakeLists.txt

ggml : remove kompute backend (#14501)

2025-07-03 07:48:32 +03:00

ggml-alloc.c

ggml: Don't assert fail when tensor data changes (#13222)

2025-05-01 22:46:10 +02:00

ggml-backend-impl.h

ggml : upgrade init_tensor API to return a ggml_status (#11854)

2025-02-28 14:41:47 +01:00

ggml-backend-reg.cpp

ggml : remove kompute backend (#14501)

2025-07-03 07:48:32 +03:00

ggml-backend.cpp

vulkan: Add fusion support for RMS_NORM+MUL (#14366)

2025-06-29 09:43:36 +02:00

ggml-common.h

ggml-cpu : split arch-specific implementations (#13892)

2025-06-09 16:47:13 +02:00

ggml-impl.h

vulkan: Add fusion support for RMS_NORM+MUL (#14366)

2025-06-29 09:43:36 +02:00

ggml-opt.cpp

mnist: fix segmentation fault (ggml/1227)

2025-05-19 13:29:56 +03:00

ggml-quants.c

ggml-quants : rename best_mad to best_error (ggml/1283)

2025-07-01 11:06:39 +03:00

ggml-quants.h

ggml : build backends as libraries (#10256)

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

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_scale_bias (#14417)

2025-07-09 18:16:12 +02:00

ggml.cpp

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

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

gguf.cpp

ggml : prevent integer overflow in gguf tensor size calculation (#14595)

2025-07-09 14:33:53 +02:00