upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
Johannes Gäßler
2026-04-09 16:42:19 +02:00
committed by GitHub
parent 009a113326
commit d6f3030047
48 changed files with 3198 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
ggml/include/ggml-backend.h
View File

@@ -68,7 +68,7 @@ extern "C" {
GGML_API void ggml_backend_buffer_reset (ggml_backend_buffer_t buffer);
// tensor copy between different backends
GGML_API void ggml_backend_tensor_copy(struct ggml_tensor * src, struct ggml_tensor * dst);
GGML_API void ggml_backend_tensor_copy(const struct ggml_tensor * src, struct ggml_tensor * dst);
//
// Backend (stream)
@@ -83,13 +83,17 @@ extern "C" {
GGML_API size_t ggml_backend_get_alignment(ggml_backend_t backend);
GGML_API size_t ggml_backend_get_max_size(ggml_backend_t backend);
GGML_API void ggml_backend_tensor_set_async(ggml_backend_t backend, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_get_async(ggml_backend_t backend, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_set_async (ggml_backend_t backend, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_get_async (ggml_backend_t backend, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_set_2d_async(ggml_backend_t backend, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
GGML_API void ggml_backend_tensor_get_2d_async(ggml_backend_t backend, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
// "offset" refers to the offset in tensor->data for setting/getting data
GGML_API void ggml_backend_tensor_set( struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_get(const struct ggml_tensor * tensor, void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_memset( struct ggml_tensor * tensor, uint8_t value, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_set ( struct ggml_tensor * tensor, const void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_get (const struct ggml_tensor * tensor, void * data, size_t offset, size_t size);
GGML_API void ggml_backend_tensor_set_2d( struct ggml_tensor * tensor, const void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
GGML_API void ggml_backend_tensor_get_2d(const struct ggml_tensor * tensor, void * data, size_t offset, size_t size, size_t n_copies, size_t stride_tensor, size_t stride_data);
GGML_API void ggml_backend_tensor_memset( struct ggml_tensor * tensor, uint8_t value, size_t offset, size_t size);
GGML_API void ggml_backend_synchronize(ggml_backend_t backend);
@@ -109,7 +113,7 @@ extern "C" {
// the copy is performed after all the currently queued operations in backend_src
// backend_dst will wait for the copy to complete before performing other operations
// automatic fallback to sync copy if async is not supported
GGML_API void ggml_backend_tensor_copy_async(ggml_backend_t backend_src, ggml_backend_t backend_dst, struct ggml_tensor * src, struct ggml_tensor * dst);
GGML_API void ggml_backend_tensor_copy_async(ggml_backend_t backend_src, ggml_backend_t backend_dst, const struct ggml_tensor * src, struct ggml_tensor * dst);
GGML_API ggml_backend_dev_t ggml_backend_get_device(ggml_backend_t backend);
@@ -135,7 +139,9 @@ extern "C" {
// integrated GPU device using host memory
GGML_BACKEND_DEVICE_TYPE_IGPU,
// accelerator devices intended to be used together with the CPU backend (e.g. BLAS or AMX)
GGML_BACKEND_DEVICE_TYPE_ACCEL
GGML_BACKEND_DEVICE_TYPE_ACCEL,
// "meta" device wrapping multiple other devices for tensor parallelism
GGML_BACKEND_DEVICE_TYPE_META,
};
// functionality supported by the device
@@ -196,7 +202,9 @@ extern "C" {
// Common functions that may be obtained using ggml_backend_reg_get_proc_address
// Split buffer type for tensor parallelism
// AllReduce operation for tensor parallelism (meta backend)
typedef bool (*ggml_backend_allreduce_tensor_t)(ggml_backend_t * backends, struct ggml_tensor ** tensors, size_t n_backends);
// Split buffer type for tensor parallelism (old)
typedef ggml_backend_buffer_type_t (*ggml_backend_split_buffer_type_t)(int main_device, const float * tensor_split);
// Set the number of threads for the backend
typedef void (*ggml_backend_set_n_threads_t)(ggml_backend_t backend, int n_threads);

3
ggml/include/ggml-cuda.h
View File

@@ -27,6 +27,9 @@ GGML_BACKEND_API bool ggml_backend_is_cuda(ggml_backend_t backend);
// device buffer
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_buffer_type(int device);
// conduct allreduce operation between devices
GGML_BACKEND_API bool ggml_backend_cuda_allreduce_tensor(ggml_backend_t * backends, struct ggml_tensor ** tensors, size_t n_backends);
// split tensor buffer that splits matrices by rows across multiple devices
GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_cuda_split_buffer_type(int main_device, const float * tensor_split);