Commit Graph
21 Commits
Author SHA1 Message Date
Oliver SimonsandAman Gupta 9e9619d030 CUDA: Add OCP FP8 support (#28413)
* Initial CUDA WIP version

* Use fp8 intrinsics

* Do W8A16 for FP8 in GEMV case

(base) osimons@ub-osimons:~/lcpp_fp8.git$ ./build-x64-linux-gcc-reldbg/bin/llama-bench -m /mnt/share/gguf/nvidia/Qwen3.6-27B-NVFP4/Qwen3.6-27B-NVFP4_fp8.gguf -p 8196 -ub 512,2048 -d 0,32000 -n 256 --load-mode dio
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 32165 MiB):
  Device 0: NVIDIA RTX PRO 4500 Blackwell, compute capability 12.0, VMM: yes, VRAM: 32165 MiB
| model                          |       size |     params | backend    | ngl | n_ubatch |         lm |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | --: | -------: | ---------: | --------------: | -------------------: |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |      512 |        dio |          pp8196 |       2781.53 ± 8.48 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |      512 |        dio |           tg256 |         37.56 ± 0.02 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |      512 |        dio | pp8196 @ d32000 |       1616.31 ± 2.61 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |      512 |        dio |  tg256 @ d32000 |         34.11 ± 0.03 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |     2048 |        dio |          pp8196 |       2542.00 ± 0.51 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |     2048 |        dio |           tg256 |         37.36 ± 0.02 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |     2048 |        dio | pp8196 @ d32000 |       1762.86 ± 1.33 |
| qwen35 27B NVFP4               |  19.56 GiB |    27.32 B | CUDA       |  -1 |     2048 |        dio |  tg256 @ d32000 |         34.09 ± 0.02 |

* Optimize GEMV kernel for FP8

* Guard __nv_cvt_fp8x2_to_bf162raw on CTK 13.2

Fixes https://github.com/ggml-org/llama.cpp/pull/28413#discussion_r4044500099

* Remove trailing whitespace

* Add supported for strided copies to/from FP8 in CUDA

* Prepare Q_reg for FP8 FlashAttention in fattn-vec.cuh

* Fix odd-rows for convert/getrows, possible with FP8

* Fix FP8 fallback in cuBlas

* Gate mmvf_f8x2_e4m3_to_bf162 on FP8 availability, i.e. CTK >= 11.8

* Restrict (fused) MMVF to 2*ts alignment, and cublas FP8 fo 16-byte

* Add todo about accumulator/precision honoring

This is beyond the scope of the stacked PR

* Avoid races in fp8_fallback

* Allow Hopper and other BW SKUs for FP8

* Use intrinsic over explicit manual conversions

* Resolve TODO

As per spec, we don't have to preserve signs

* Add commend on cublaslt workspaces

* Use convert_unary_cont_cuda over block dequant in convert.cu

* Use get_rows_cuda_float for fp8 kv cache

* Make FP8 copies work on all IHV's

* More cleanup

* Simplify by falling back to shared cuBLAS helper

* Fuse weight_scale multiplication for FP8 also

* More code-cleanup

* Guard __nv_cvt_fp8x2_to_bf162raw on CTK 13.4

Only cvt.rn.bf16x2.e4m3x2 is exposed from 13.2 onwards, so
93e98b9203dfacb85f9ac665f5f0482a8c6b4192 was incorrect fix

* Use F32 activations in fallback mmvf path

* Explicitly link against cublaslt

* Move FP8 conversion intrinsics into ggml_cuda_cast

Cleaner this way

* WIP src1/prec for fp8 in MMVF

* Remove comment

* Keep only f8 x f8 KV cache for now

* Just do FP8 x FP32 x FP32 in MMVF as its fast enough

* Update ggml/src/ggml-cuda/ggml-cuda.cu

Co-authored-by: Aman Gupta <amangupta052@gmail.com>

* Add batched FP8 GEMMS in cublas as suggested by code review

https://github.com/ggml-org/llama.cpp/pull/28413#issuecomment-6676015644

* Extract fp8x2 -> float2 load into helper

* Searapte copy checks to/from fp8

* Compiler massaging to avoid repeated address offsets

---------

Co-authored-by: Aman Gupta <amangupta052@gmail.com>
2026-11-11 10:44:30 +02:00
Michael Taylor dd002b91f5 sycl: fix compiler warnings - missing prototypes, dead code, extra semicolons (#30271) 2026-10-20 00:47:25 -04:00
Sarah Wu 0c6a6a7ce5 Enables Windows ARM64 build with MSVC cl.exe (#28362)
* can reproduce the issue vlad sees

* fix fma issue

* drop volatile

* fix volatile runtime task

* add arm flag if needed

* fix hsum compile error

* fix syntax in quants

* strengthen sve probing

* make the syntax fixes one liners

* remove debug code

* formatting

* remove macro for float

* drive down gcc instruction count

* support armec

* fix CI comments

address CI comments

fix cross compile issue

remove warning

fix style and fix fma probing

fix style

* add documentation

* update documentation
2026-09-28 10:07:27 +02:00
Piotr Wilkin (ilintar)andJohannes Gäßler 5a4d0fecae CUDA: replace GGML_FA_ALL_QUANTS with GGML_FA_QUANTS, more control over what is compiled (#28079)
* CUDA: add configurable FA quant combinations

Assisted-by: Codex

* remove all flags but , add runtime fallback with warning for uncompiled combination

* Update docs/build.md

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

* apply code review comments

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2026-09-09 12:50:08 +02:00
Jonathan Clohessy d222767c7a kleidiai: Rework KleidiAI Build System/Integration (#26077)
* Rework KleidiAI Build System/Integration

Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com>

* Add fp16 guard, and fix cmake caching issue

Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com>

* Fix formatting, and rebase issue

Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com>

---------

Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com>
2026-08-25 14:07:29 -07:00
Daniel Bevenius 13fd0bb55e cmake : add config version support (ggml/1582)
* cmake : add config version support (wip) [no ci]

This commit adds support for find_package using a version, for example:
```
find_package(ggml 0.19.0 REQUIRED)
```

examples/test-cmake has been updated to use this and build scripts have
been added to verify this manually. This is still a work in progress and
I'm not sure about the scripts and if we can find better ways to test
this but it might be useful to have for verification of changes to the
cmake build.

* cmake : add semver to ggml backends [no ci]

This commit adds a semver to the ggml backend modules files.

The motivation for this is that the backends are currently loaded just a
file extension, for example .so on linux. With the introduction of
semantic versioning installing a new version should just work but since
these files don't have a version they would get overwritten. Adding the
semver to the library names allows multiple version to be supported and
the correct one will be loaded by the code.

I've only tested this on linux and need to test on mac and win.

* Revert "cmake : add semver to ggml backends [no ci]"

This reverts commit 53a6c58a07591951324c891b9986b2cffe5c7972.

* examples : update build-install.sh and set GGML_BACKEND_DIR
2026-08-12 14:23:43 +03:00
Jeff Bolz 826539ce59 ggml : Parallelize quant LUT init (#23595)
- Use OpenMP to parallelize iq2xs_init_impl and iq3xs_init_impl.
- Move the OpenMP detection from ggml-cpu to ggml-base.
- Update OpenMP dependencies in ggml-config.cmake.in.
2026-05-25 10:15:46 +03:00
d6f3030047 ggml: backend-agnostic tensor parallelism (experimental) (#19378)
* ggml: backend-agnostic tensor parallelism

* support for GPT-OSS, Qwen 3 MoE

* partial Vulkan fix

* add support for 4/8 GPUs

* unconditional peer access

* re-use buffers + ggml contexts

* fix output pattern

* NCCL support

* GGML: HIP: add RCCL support

* Remove shfl and AllReduce from backend interface

* move allocation workaround out of ggml-alloc.c

* 2d tensor set/get support

* Fix the seg fault without NCCL

* Apply suggestion from JohannesGaessler

* support for tensor dims % n_devs != 0

* fix view_offs scaling

* arbitrary num. of GPUs/tensor split

* fix compilation

* better granularity estimate

* Support device-specific host buffer types if all underlying backends expose the same type. This allows using pinned memory instead of pageable memory for CUDA.

Fix compilation errors.

* partial Qwen 3 Next support

* Fix qwen3 30b (#8)

* Fix crash with Qwen-30B-A3B Q4_0

Qwen-30B-A3B Q4_0 has an intermediate dimension of 768. Using a granularity of 256 forces an uneven split between GPUs, which is not supported by the current implementation.

* Decide block size based on tensor quantization type

* Fix crashes due to KV cache serialization (#9)

KV cache serialization requires non-zero offsets on the tensor. Add support in the meta backend to set/get a tensor with a non-zero offset.

* metal : fix build (#7)

* static memory allocations, fix usage count

* fix tensor granularity

* more even memory distribution

* use BF16 for allreduce

* rebase fixup

* better error message for unsupported architectures

* Fix device mismatch during scatter of allReduce. (#11)

There is a mismatch between the dst buffer device and the backend device, causing the use of sync copies

* Enable the previous allreduce implementation. It is better in both perf and stability (#12)

* delay AllReduce for Moe for less I/O

* build : clean-up compile warnings

* backend : move most of the meta backend API to ggml-backend-impl.h

* cont : hide unused public API in the implementation

* llama : use llama_device + remove ggml_backend_dev_is_meta()

* ggml-backend : remove unused alloc include

* minor : remove regex include

* ggml : introduce ggml-ext.h for staging new APIs

* rebase fixup

* fix tests

* llama : more robust logic for determining Meta devices (#16)

* llama : more robust logic for determining Meta devices

* cont : fix devs size check

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

* cont : fix log type

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

---------

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

* disable roundtrip for meta backend

* fix arch selection

* Qwen 3.5 support

* fix Gemma 4 MoE

* fix OpenVino, SYCL

* fix test-llama-archs for CPU-only builds

* Fix Qwen 3.5 MoE

* disable meta backend tests for WebGPU

* tests : filter CPU-based devices from the Meta backend tests (#17)

* meta : formatting, naming, indentation (#18)

* formatting : llama-model.cpp

* formatting : ggml-ext.h

* formatting : ggml-backend-meta.cpp

* meta : add TODO

* add documentation

* better error messages

* fix GPT-OSS

---------

Co-authored-by: Carl Philipp Klemm <carl@uvos.xyz>
Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-04-09 16:42:19 +02:00
Christian Kastner 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)
Any available libraries are found and loaded dynamically at runtime.
2025-08-07 13:45:41 +02:00
Christian Kastner 41613437ff cmake: Add GGML_BACKEND_DIR option (#15074)
* cmake: Add GGML_BACKEND_DIR option

This can be used by distributions to specify where to look for backends
when ggml is built with GGML_BACKEND_DL=ON.

* Fix phrasing
2025-08-04 21:29:14 +02:00
Kai Pastor e228de9449 cmake : Fix BLAS link interface (ggml/1316) 2025-07-30 17:33:11 +03:00
Kai Pastor 613c5095c3 cmake : Indent ggml-config.cmake (ggml/1310) 2025-07-28 08:15:01 +03:00
Kai Pastor 60f816a79d cmake : fix usage issues (ggml/1257)
* CMake config: Create target only once

Fix error on repeated find_package(ggml).
For simplicity, check only for the top-level ggml::ggml.

* CMake config: Add CUDA link libs

* CMake config: Add OpenCL link libs

* CMake config: Use canonical find_dependency

Use set and append to control link lib variables.
Apply more $<LINK_ONLY...>.

* CMake config: Wire OpenMP dependency
2025-07-24 20:27:23 +03:00
xctan 3555b3004b ggml-cpu : rework weak alias on apple targets (#14146)
* ggml-cpu : rework weak alias on apple targets

* fix powerpc detection

* fix ppc detection

* fix powerpc detection on darwin
2025-06-16 13:54:15 +08:00
Christian Kastner 21fcc21ad5 cmake: Factor out CPU architecture detection (#13883)
* cmake: Define function for querying architecture

The tests and results match exactly those of ggml/src/CMakeLists.txt

* Switch arch detection over to new function
2025-05-29 12:50:25 +02:00
Georgi Gerganov 771d84371c scripts : update sync + fix cmake merge
ggml-ci
2025-03-27 10:09:29 +02:00
Christian Kastner 374101fd74 cmake : enable building llama.cpp using system libggml (#12321)
* cmake: Factor out compiler flag function from ggml

llama.cpps's build requires it, too, and we may want to make use of it
without add_subdirectory(ggml).

* cmake: Enable building against system ggml

This facilitates package maintenance for Linux distributions, where the
libggml library most likely will be shipped as an individual package
upon which a llama.cpp package depends.
2025-03-17 11:05:23 +02:00
Vladimir Vuksanovic b95c8af37c cmake: Fix ggml backend dependencies and installation (#11818)
* Fix dependencies between ggml and backends

ggml backends link only to ggml-base and ggml links to all backends.

* Fix installation of ggml backends

Set up GNUInstallDirs before setting the installation directory of ggml backends
2025-02-27 09:42:48 +02:00
bandotiandGeorgi Gerganov 19f65187cb cmake: add ggml find package (#11369)
* Add initial ggml cmake package

* Add build numbers to ggml find-package

* Expand variables with GGML_ prefix

* Guard against adding to cache variable twice

* Add git to msys2 workflow

* Handle ggml-cpu-* variants

* Link ggml/ggml-base libraries to their targets

* Replace main-cmake-pkg with simple-cmake-pkg

* Interface features require c_std_90

* Fix typo

* Removed unnecessary bracket from status message

* Update examples/simple-cmake-pkg/README.md

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

* Update examples/simple-cmake-pkg/README.md

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

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-01-26 12:07:48 -04:00
ae8de6d50a ggml : build backends as libraries (#10256)
* ggml : build backends as libraries

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: R0CKSTAR <xiaodong.ye@mthreads.com>
2024-11-14 18:04:35 +01:00
Georgi Gerganovandslaren f3f65429c4 llama : reorganize source code + improve CMake (#8006)
* scripts : update sync [no ci]

* files : relocate [no ci]

* ci : disable kompute build [no ci]

* cmake : fixes [no ci]

* server : fix mingw build

ggml-ci

* cmake : minor [no ci]

* cmake : link math library [no ci]

* cmake : build normal ggml library (not object library) [no ci]

* cmake : fix kompute build

ggml-ci

* make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE

ggml-ci

* move public backend headers to the public include directory (#8122)

* move public backend headers to the public include directory

* nix test

* spm : fix metal header

---------

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

* scripts : fix sync paths [no ci]

* scripts : sync ggml-blas.h [no ci]

---------

Co-authored-by: slaren <slarengh@gmail.com>
2024-06-26 18:33:02 +03:00