HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced new reference refs/tags/b8021 to happyz/llama.cpp from mirror 2026-02-13 06:02:35 -08:00
happyz synced commits to refs/tags/b8022 at happyz/llama.cpp from mirror 2026-02-13 06:02:35 -08:00
happyz synced new reference refs/tags/b8022 to happyz/llama.cpp from mirror 2026-02-13 06:02:35 -08:00
happyz synced new reference refs/tags/b8017 to happyz/llama.cpp from mirror 2026-02-13 06:02:34 -08:00
happyz synced commits to refs/tags/b8018 at happyz/llama.cpp from mirror 2026-02-13 06:02:34 -08:00
happyz synced new reference refs/tags/b8018 to happyz/llama.cpp from mirror 2026-02-13 06:02:34 -08:00
happyz synced commits to refs/tags/b8020 at happyz/llama.cpp from mirror 2026-02-13 06:02:34 -08:00
happyz synced commits to refs/pull/19558/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
6c6bc56813 Merge c3f8de0e0c into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 14 commits »
happyz synced commits to refs/pull/19566/head at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
d812b6955b Update ggml/src/ggml-cuda/ggml-cuda.cu
happyz synced commits to refs/pull/19569/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
37186c7b2d Merge 72a0175dde into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 14 commits »
happyz synced commits to refs/pull/19573/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
62b567c6ae Merge e808daec68 into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 14 commits »
happyz synced commits to refs/tags/b8017 at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
happyz synced commits to refs/pull/19572/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:33 -08:00
68791f3600 Merge db4a5a84fc into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 14 commits »
happyz synced commits to refs/pull/19547/head at happyz/llama.cpp from mirror 2026-02-13 06:02:32 -08:00
1bb128d3e6 pre-downsample position embeddings during GGUF conversion for fixed input size
a565bbd1b4 simplified code; addressed reviews
Compare 2 commits »
happyz synced commits to refs/pull/19547/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:32 -08:00
092283af46 Merge 1bb128d3e6 into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
1bb128d3e6 pre-downsample position embeddings during GGUF conversion for fixed input size
b2ecc0cdb4 support --verbose-prompt (#19576)
Compare 16 commits »
happyz synced commits to refs/pull/19553/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:32 -08:00
9cacc020e1 Merge f36fcfb825 into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 16 commits »
happyz synced commits to refs/pull/19557/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:32 -08:00
8aff19ba65 Merge 4836df97b9 into cc2aa81513
cc2aa81513 Fix wrong memcpy length for block_interleave == 4 (#19575)
0e21991472 fix vulkan ggml_acc only works in 3d but not 4d (#19426)
b2ecc0cdb4 support --verbose-prompt (#19576)
5065da554e CUDA: loop over ne2*ne3 in case it overflows (#19538)
Compare 14 commits »
happyz synced commits to refs/pull/19531/head at happyz/llama.cpp from mirror 2026-02-13 06:02:31 -08:00
a46782c1b7 Merge branch 'ggml-org:master' into Kimi-Linear
25224c8021 llama : remove deprecated codecvt (#19565)
2f5d8f8edc vendor : update BoringSSL to 0.20260211.0 (#19562)
bb96bfd361 memory : fix kv cache size for hybrid models (#19559)
0644baefde metal : improve concurrency (#19555)
Compare 22 commits »
happyz synced commits to refs/pull/19532/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:31 -08:00
7215d278c2 Merge 0985954117 into 423cf0b26f
423cf0b26f docs : fix broken link and typo (#19560)
33a56f90a6 model : Kimi Linear fix conv state update (#19531)
25224c8021 llama : remove deprecated codecvt (#19565)
2f5d8f8edc vendor : update BoringSSL to 0.20260211.0 (#19562)
Compare 10 commits »
happyz synced commits to refs/pull/19535/merge at happyz/llama.cpp from mirror 2026-02-13 06:02:31 -08:00
dc6942020e Merge 36f28fe8b9 into 423cf0b26f
423cf0b26f docs : fix broken link and typo (#19560)
33a56f90a6 model : Kimi Linear fix conv state update (#19531)
25224c8021 llama : remove deprecated codecvt (#19565)
2f5d8f8edc vendor : update BoringSSL to 0.20260211.0 (#19562)
Compare 8 commits »