HappyZ happyz
0 Followers · 0 Following
Repositories
18
 Projects Packages Public Activity Starred Repositories
happyz synced commits to refs/pull/7267/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:58 -07:00
91bee717aa Merge 2a9a84be7d into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/7225/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:57 -07:00
3e60809d79 Merge 38b348e28fc83ca701a7620af691cf9eeac0b615 into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/7239/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:57 -07:00
c2ea92740f Merge f4f5b7ac56 into ea3b0590ee
ea3b0590ee embedding : free the batch after execution (#7297)
29499bb593 sync : ggml
48aa8fd1f2 ggml : add `ggml_upscale_ext` (ggml/814)
583fd6b000 server bench: fix bench not waiting for model load (#7284)
Compare 5 commits »
happyz synced commits to refs/pull/7237/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:57 -07:00
bd37d6f971 Merge 9c5d3fcffb into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/7198/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:57 -07:00
274daed3de Merge cc3df3f388 into 583fd6b000
583fd6b000 server bench: fix bench not waiting for model load (#7284)
Compare 2 commits »
happyz synced commits to refs/pull/7191/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:57 -07:00
2dc2128633 Merge ece01fc2e9 into dc020985b8
ece01fc2e9 matmul-int8: remove unnecessary casts in q8_0_q8_0
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
Compare 9 commits »
happyz synced commits to refs/pull/7117/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:56 -07:00
87d4bb41f1 Merge 58551d0bd2 into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/7154/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:56 -07:00
e77c023b1e Merge d7359a389c into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/7191/head at happyz/llama.cpp from mirror 2024-05-15 10:41:56 -07:00
ece01fc2e9 matmul-int8: remove unnecessary casts in q8_0_q8_0
happyz synced commits to refs/pull/7020/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:56 -07:00
ceaa7b23e5 Merge 85263f0568 into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 54 commits »
happyz synced commits to refs/pull/6958/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
dcb2e57317 Merge aa6f4c280b into 583fd6b000
583fd6b000 server bench: fix bench not waiting for model load (#7284)
9f773486ab script : sync ggml-rpc
e8a7fd4fb0 metal : support FA without mask + add asserts (#7278)
a5e3fde857 sync : ggml
Compare 11 commits »
happyz synced commits to refs/pull/6919/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
dc5cfb80e1 Merge f0d7be409d into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/6915/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
e15cbc01c5 Merge 14c104d166 into dc020985b8
14c104d166 Update ggml.c
f2aabab436 Update ggml.c
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
Compare 10 commits »
happyz synced commits to refs/pull/7020/head at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
85263f0568 Minor fixes after merging.
7a5df5fbd5 Merge branch 'ggerganov:master' into snowflake-arctic
f4421f7cd8 convert-hf : Corrected sentencepiece API calls.
583fd6b000 server bench: fix bench not waiting for model load (#7284)
9f773486ab script : sync ggml-rpc
Compare 57 commits »
happyz synced commits to refs/pull/6999/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
4a640cb235 Merge cb324f48f488e66321783fc0507cda7b7b993e56 into ea3b0590ee
ea3b0590ee embedding : free the batch after execution (#7297)
29499bb593 sync : ggml
48aa8fd1f2 ggml : add `ggml_upscale_ext` (ggml/814)
583fd6b000 server bench: fix bench not waiting for model load (#7284)
Compare 5 commits »
happyz synced commits to refs/pull/6988/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:55 -07:00
a83b8fb35a Merge a808370c58 into 583fd6b000
583fd6b000 server bench: fix bench not waiting for model load (#7284)
Compare 2 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:54 -07:00
d6412bb63d Merge 49e078f79d into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/6840/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:54 -07:00
4bc45eae97 Merge bb3a5274c7c1efd883f7e57edb849c0394d2c91d into dc020985b8
dc020985b8 Avoid unnecessarily disabling CUDA graphs (#7302)
344f9126cc ggml : tag ggml_tensor::backend as deprecated (#7290)
9a17ab914b Add missing " (#7303)
ea3b0590ee embedding : free the batch after execution (#7297)
Compare 8 commits »
happyz synced commits to refs/pull/6866/merge at happyz/llama.cpp from mirror 2024-05-15 10:41:54 -07:00
5032b646c8 Merge d12c57b559 into 583fd6b000
583fd6b000 server bench: fix bench not waiting for model load (#7284)
9f773486ab script : sync ggml-rpc
e8a7fd4fb0 metal : support FA without mask + add asserts (#7278)
a5e3fde857 sync : ggml
Compare 22 commits »
happyz synced commits to refs/pull/6915/head at happyz/llama.cpp from mirror 2024-05-15 10:41:54 -07:00
14c104d166 Update ggml.c
f2aabab436 Update ggml.c
Compare 2 commits »