Block a user
root
synced and deleted reference 2024-09-22 04:56:20 +00:00
refs/tags/refs/pull/9454/merge
at root/llama.cpp from mirror
root
synced and deleted reference 2024-09-22 04:56:20 +00:00
refs/tags/refs/pull/9574/merge
at root/llama.cpp from mirror
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
root
synced commits to update_flake_lock_action at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
db660f5a40
flake.lock: Update
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
63351143b2
quantize : improve type name parsing (#9570)
root
synced commits to refs/pull/8208/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
6690aa6089
Merge
256707309f
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
63351143b2
quantize : improve type name parsing (#9570)
root
synced commits to refs/pull/9058/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
9508d245f6
Merge
fc6abde7aa
into ecd5d6b65b
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
root
synced commits to refs/pull/9096/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
2f4fc576ec
Merge
7323304092
into ecd5d6b65b
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
root
synced commits to refs/pull/9186/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
80867c8063
Merge
63b6e73500
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
root
synced commits to refs/pull/9325/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
28bffb5f08
Merge
b979fc97ba
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
root
synced commits to refs/pull/9438/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
c671f109e3
Merge
2615459bb2
into ecd5d6b65b
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
caeba159da
Merge branch 'master' into wkv-cuda
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
63351143b2
quantize : improve type name parsing (#9570)
root
synced commits to refs/pull/9482/merge at root/llama.cpp from mirror
2024-09-22 04:56:20 +00:00
d133f32fbe
Merge
e08b907760
into ecd5d6b65b
ecd5d6b65b
llama: remove redundant loop when constructing ubatch (#9574)
2a63caaa69
RWKV v6: RWKV_WKV op CUDA implementation (#9454)
root
synced and deleted reference 2024-09-21 20:46:21 +00:00
refs/tags/sycl-fallback-mmvq
at root/llama.cpp from mirror
root
synced commits to refs/pull/8837/merge at root/llama.cpp from mirror
2024-09-21 20:46:21 +00:00
982380d71d
Merge
02c75452c1
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
root
synced commits to refs/pull/8878/merge at root/llama.cpp from mirror
2024-09-21 20:46:21 +00:00
794aaf8ccd
Merge
bb668b608e
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
root
synced commits to refs/pull/9096/merge at root/llama.cpp from mirror
2024-09-21 20:46:21 +00:00
eb1039dbff
Merge
7323304092
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
root
synced commits to refs/pull/9209/merge at root/llama.cpp from mirror
2024-09-21 20:46:21 +00:00
6e2389b050
Merge
951f1d9053
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
root
synced commits to refs/pull/9217/merge at root/llama.cpp from mirror
2024-09-21 20:46:21 +00:00
2eda3d9ac6
Merge
71cf0e1c0f
into d09770cae7
d09770cae7
ggml-alloc : fix list of allocated tensors with GGML_ALLOCATOR_DEBUG (#9573)
41f477879f
Update CUDA graph on scale change plus clear nodes/params (#9550)
e948a7da7a
CI: Provide prebuilt windows binary for hip (#9467)
63351143b2
quantize : improve type name parsing (#9570)