 leejetandJohannes Gäßler
|
4f4246dcb4
|
ggml: fix cuda kernel launch configuration for k_compute_batched_ptrs to support large batch (llama/16744)
* fix k_compute_batched_ptrs
* add backend ops test
* Update ggml/src/ggml-cuda/ggml-cuda.cu
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* reduce the batch size
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
|
2025-11-09 23:38:03 +02:00 |
|
|
leejet
|
5166efa7f0
|
ggml: fix CUDA grid launch condition for large block_nums.y in binbcast (llama/16742)
* Fix CUDA grid launch condition for large block_nums.y
* add backend ops test
* reduce test repetitions
|
2025-11-09 23:38:03 +02:00 |
|
|
leejetandJeff Bolz
|
2228462b19
|
ggml: add ops for WAN video model (cuda && cpu) (llama/15669)
* add conv3d support
* add ggml_pad_ext for cpu & cuda backend
* cuda/cpu: add im2col_3d support
* cuda: make im2col a little faster
* fix cuda pad/scale/im2col3d
* make im2col_3d faster
* gguf: support loading tensors which n_dims > GGML_MAX_DIMS
* fix cuda get_rows
* avoid ggml_conv_3d conflict
* correct GGML_OP_COUNT assertion
* avoid build failure
* avoid build failure on MacOS
* cuda: remove unnecessary MIN define
* fix cpu im2col_3d
* adjust the code style
* cuda: use simpler loop in get_rows
* add test_im2col_3d to test-backend-ops
* test-backend-ops.cpp: remove trailing whitespace
* cpu: im2col_3d support non continuous src
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
* fix test_im2col_3d
* remove unused variables
* cuda: get_rows: dfloat2 -> float2
* add test_pad_ext to test-backend-ops.cpp
* add gguf_init_from_file_ext impl
* Revert "gguf: support loading tensors which n_dims > GGML_MAX_DIMS"
This reverts commit d8377a0a37f314bd3713fe043b4333ad661610c1.
* Revert "add gguf_init_from_file_ext impl"
This reverts commit d9f1d13208c68ef83b3538201ac7f31614fb1994.
* update ggml_backend_vk_device_supports_op
* fix ggml_backend_vk_device_supports_op
* update other backend supports op for ggml_pad_ext
* metal/opencl/sycl/vulkan: fix GGML_OP_PAD check in supports_op
---------
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
|
2025-09-20 13:42:49 +03:00 |
|
|
leejet
|
a3123e105b
|
cuda: make im2col a little faster (llama/15025)
|
2025-08-18 20:30:45 +03:00 |
|
|
|
8cee7c08b6
|
add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)
* cuda: fix group_norm
* cuda: add batch inference support for ggml_pad/ggml_upscale
* add ggml_arrange
* add ggml_timestep_embedding
* update ggml_arange/ggml_timestep_embedding tests
* cuda: fix im2col
* add ggml_arange/ggml_timestep_embbeding support for metal backend
* fix some bugs
* fix some bugs
* Update ggml.h
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml-cuda.cu
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml-metal.m
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml-metal.m
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Update ggml-metal.metal
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* modify according to the review comments
* ggml : fix compile warnings + code style
* ggml : normalize compute_forward calls + fix seg fault in debug
* minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: slaren <slarengh@gmail.com>
|
2024-03-08 11:38:31 +02:00 |
|
|
leejet
|
e66a9a7806
|
ggml : change GGML_MAX_NAME at compile time (ggml/682)
* change GGML_MAX_NAME to 128
* allow controlling the value of GGML_MAX_NAME through external macro definitions
|
2024-01-11 21:50:00 +02:00 |
|