Commit Graph

13 Commits

Author SHA1 Message Date
33983057d0 musa: Upgrade MUSA SDK version to rc4.0.1 and use mudnn::Unary::IDENTITY op to accelerate D2D memory copy (#13647)
* musa: fix build warning (unused parameter)

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: upgrade MUSA SDK version to rc4.0.1

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

* musa: use mudnn::Unary::IDENTITY op to accelerate D2D memory copy

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

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

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

* musa: remove MUDNN_CHECK_GEN and use CUDA_CHECK_GEN instead in MUDNN_CHECK

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>

---------

Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
2025-05-21 09:58:49 +08:00
9998540149 cuda : fix unused variable compile warning (whisper/0)
ggml-ci
2025-05-01 09:58:44 +03:00
e291450b76 musa: fix build warning (#13129)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2025-04-27 13:22:49 +02:00
207c22ec2d ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (#12970) 2025-04-17 15:19:42 +02:00
7538246e7c cuda : add f32 to bf16 copy op (#12806)
This allows BF16 KV-cache on CUDA.
2025-04-08 23:21:31 +02:00
916c83bfe7 musa: fix compilation warnings in mp_22/31 (#12780)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2025-04-06 15:23:54 +02:00
3f9da22c2b Simplify and improve CUDA graphs through use of indirect copy pointers (#9017)
* CUDA: Simplify and improve CUDA graphs through use of indirect copy pointers

Previously there was complexity in the CUDA graphs implementation due
frequently changing parameters to copy kernels associated with K and V
cache pointers. This patch simplifies by using indirection to avoid
such parameters frequently changing, avoiding the need for frequent
graph updates.

Fixes #12152

* Addressed comments

* fix HIP builds

* properly sync to stream

* removed ggml_cuda_cpy_fn_ptrs

* move stream sync before free

* guard to only use indirection with graphs

* style fixes

* check for errors

---------

Co-authored-by: slaren <slarengh@gmail.com>
2025-04-03 03:31:15 +02:00
d70908421f cuda: Add Q5_1, Q5_0, Q4_1 and Q4_0 to F32 conversion support. (#12000) 2025-02-22 09:43:24 +01:00
116efee0ee cuda: add q8_0->f32 cpy operation (#9571)
llama: enable K-shift for quantized KV cache
It will fail on unsupported backends or quant types.
2024-09-24 02:14:24 +02:00
4db04784f9 cuda : fix defrag with quantized KV (#9319) 2024-09-05 11:13:11 +02:00
2b1f616b20 ggml : reduce hash table reset cost (#8698)
* ggml : reduce hash table reset cost

* fix unreachable code warnings after GGML_ASSERT(false)

* GGML_ASSERT(false) -> GGML_ABORT("fatal error")

* GGML_ABORT use format string
2024-07-27 04:41:55 +02:00
07a3fc0608 Removes multiple newlines at the end of files that is breaking the editorconfig step of CI. (#8258) 2024-07-02 12:18:10 -04:00
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