HappyZ happyz
happyz synced commits to dependabot/go_modules/modernc.org/sqlite-1.29.8 at happyz/memos from mirror 2024-04-22 11:13:39 -07:00
happyz synced new reference dependabot/go_modules/modernc.org/sqlite-1.29.8 to happyz/memos from mirror 2024-04-22 11:13:39 -07:00
happyz synced commits to refs/pull/6796/head at happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
6b220dca32 Help clang produce fma instructions
9d4d14c9b0 Address review comments
Compare 2 commits »
happyz synced new reference refs/tags/b2710 to happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
happyz synced commits to refs/tags/b2710 at happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
happyz synced commits to refs/pull/6796/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
6b220dca32 Help clang produce fma instructions
9d4d14c9b0 Address review comments
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
Compare 4 commits »
happyz synced commits to refs/pull/6784/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
Compare 2 commits »
happyz synced commits to refs/pull/6781/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:05 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 5 commits »
happyz synced commits to refs/pull/6658/head at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
8360e0c960 no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators.
happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 8 commits »
happyz synced commits to refs/pull/6766/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
Compare 2 commits »
happyz synced commits to refs/pull/6739/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 5 commits »
happyz synced commits to refs/pull/6658/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
8360e0c960 no need to add a NUL to the std::vector, std::string can be initialized from a pair of iterators.
Compare 2 commits »
happyz synced commits to refs/pull/6648/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:04 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
Compare 2 commits »
happyz synced commits to refs/pull/6445/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:03 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
Compare 2 commits »
happyz synced commits to refs/pull/6563/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:03 -07:00
f78dfe2f6d Merge 9acb43d7fa0b8da867570c975d33f0728951ca46 into 5cf5e7d490
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6511/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:03 -07:00
e5758e5754 Merge a6f54dee3ca65ae1dbeab3f8c26c1d75a9609715 into 5cf5e7d490
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
Compare 3 commits »
happyz synced commits to refs/pull/6602/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:03 -07:00
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 10 commits »
happyz synced commits to refs/pull/6522/merge at happyz/llama.cpp from mirror 2024-04-21 23:14:03 -07:00
2a4f667265 Merge a37d88568336ec949865e166eaf1454841f4cdb5 into 5cf5e7d490
5cf5e7d490 `build`: generate hex dump of server assets during build (#6661)
40f74e4d73 llama : add option to render special/control tokens (#6807)
b9cc76d87e ggml : fix ggml_backend_cpu_supports_op() for CPY (#0)
7dbdba5690 llama : add llama-3 chat template (#6751)
Compare 11 commits »
happyz synced commits to refs/pull/6412/head at happyz/llama.cpp from mirror 2024-04-21 23:14:02 -07:00
c2cc0ddf7e Fix documentation
b7a9144c96 Make the GGML header look nicer
50ceb15d0e Remove bf16 luts
9cedb3ad0f Minimize the GGML API surface area for BF16
8377c4628c Remove GGML code that's not needed
Compare 110 commits »