HappyZ happyz
happyz synced commits to refs/pull/7522/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:52 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 11 commits »
happyz synced commits to refs/pull/7514/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:52 -07:00
23fd1b587c update debug statements
07dba13ab6 temporary commit while I move dev environments
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
Compare 6 commits »
happyz synced commits to refs/pull/7499/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:51 -07:00
af1afb0b5f Merge 00ff73a90101c76108131a5867a3c3c78a42ee8c into bde7cd3cd9
00ff73a901 convert-*.py: fix regression to write to same directory as dir_model
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
51953beb32 convert-*.py: fix various runtime error
79d39767d2 convert-*.py: add heuristic to directory name fallback
Compare 14 commits »
happyz synced commits to refs/pull/7514/head at happyz/llama.cpp from mirror 2024-06-03 18:19:51 -07:00
23fd1b587c update debug statements
07dba13ab6 temporary commit while I move dev environments
Compare 2 commits »
happyz synced commits to refs/pull/7504/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:51 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 18 commits »
happyz synced commits to refs/pull/7488/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:50 -07:00
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
a10cda58d3 cmake : add pkg-config spec file for llama.cpp (#7702)
Compare 11 commits »
happyz synced commits to refs/pull/7499/head at happyz/llama.cpp from mirror 2024-06-03 18:19:50 -07:00
00ff73a901 convert-*.py: fix regression to write to same directory as dir_model
51953beb32 convert-*.py: fix various runtime error
79d39767d2 convert-*.py: add heuristic to directory name fallback
fce04a23b8 convert-*.py: need to include self in per_model_weight_count_estimation()
99ecddf8dd convert-*.py: refactor parameter weight class
Compare 10 commits »
happyz synced commits to refs/pull/7497/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:50 -07:00
c4c7d6d306 Merge 46c0cd78ef103d83cbec3d8d0dbd36574f0dd889 into bde7cd3cd9
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 11 commits »
happyz synced commits to refs/pull/7286/head at happyz/llama.cpp from mirror 2024-06-03 18:19:49 -07:00
eb42fb79da refactor format
happyz synced commits to refs/pull/7286/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:49 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
eb42fb79da refactor format
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
Compare 5 commits »
happyz synced commits to refs/pull/7379/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:49 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 5 commits »
happyz synced commits to refs/pull/7487/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:49 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 5 commits »
happyz synced commits to refs/pull/7472/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:49 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 62 commits »
happyz synced commits to refs/pull/7246/head at happyz/llama.cpp from mirror 2024-06-03 18:19:48 -07:00
174bb3bcd6 Merge branch 'gguf-model-template' of github.com:teleprint-me/llama.cpp into gguf-model-template
3c23d9f91e Merge branch 'master' into gguf-model-template
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
Compare 127 commits »
happyz synced commits to refs/pull/7267/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:48 -07:00
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 71 commits »
happyz synced commits to refs/pull/7187/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:48 -07:00
6250f06dac Merge 30df9d3165e14396000055fbe090de4df30d4e37 into a5735e4426
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
Compare 3 commits »
happyz synced commits to refs/pull/7246/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:48 -07:00
174bb3bcd6 Merge branch 'gguf-model-template' of github.com:teleprint-me/llama.cpp into gguf-model-template
3c23d9f91e Merge branch 'master' into gguf-model-template
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
Compare 40 commits »
happyz synced commits to refs/pull/6942/head at happyz/llama.cpp from mirror 2024-06-03 18:19:47 -07:00
c8ecbc67e2 oops, actually fix gguf_writer placement
efead0408c fix gguf_writer placement and remove comments
Compare 2 commits »
happyz synced commits to refs/pull/6840/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:47 -07:00
11910802fc Merge 0629a79d032d1dbfbc25a6ef40e830e895ed2660 into bde7cd3cd9
bde7cd3cd9 llama : offload to RPC in addition to other backends (#7640)
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
3d7ebf6312 Vulkan Mixture of Experts (MoE) support (#7628)
Compare 7 commits »
happyz synced commits to refs/pull/6869/merge at happyz/llama.cpp from mirror 2024-06-03 18:19:47 -07:00
81a907d68e Merge 525884d0dbcac8cb07a5e95e9d847c6df185385d into a5735e4426
a5735e4426 ggml : use OpenMP as a thread pool (#7606)
0b832d53ba make: fix debug options not being applied to NVCC (#7714)
Compare 3 commits »