• Joined on 2024-09-10
root synced new reference gg/cmake-dedup-link to root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
root synced commits to gg/cmake-defaults at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
root synced new reference gg/cmake-defaults to root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
root synced commits to gg/log at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
078be074a7 log : print if build is debug [no ci]
2948768e25 common : reimplement the logger
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
Compare 6 commits »
root synced commits to gg/metal-zero-allocs at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
root synced new reference gg/metal-zero-allocs to root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
root synced commits to master at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
Compare 2 commits »
root synced commits to refs/pull/8210/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
e665744317 llava : fix the script error in MobileVLM README (#9054)
Compare 77 commits »
root synced commits to refs/pull/8837/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
e665744317 llava : fix the script error in MobileVLM README (#9054)
Compare 15 commits »
root synced commits to refs/pull/9034/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
Compare 42 commits »
root synced commits to refs/pull/9078/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
Compare 4 commits »
root synced commits to refs/pull/9090/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
Compare 3 commits »
root synced commits to refs/pull/9096/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
Compare 3 commits »
root synced commits to refs/pull/9131/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
Compare 79 commits »
root synced commits to refs/pull/9186/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
Compare 3 commits »
root synced commits to refs/pull/9209/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
Compare 3 commits »
root synced commits to refs/pull/9217/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
274da00a11 Merge 71cf0e1c0f3248fb34f32fc06a7e0c5b4bd658e2 into 0abc6a2c25
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
78203641fe server : Add option to return token pieces in /tokenize endpoint (#9108)
Compare 4 commits »
root synced commits to refs/pull/9322/merge at root/llama.cpp from mirror 2024-09-13 08:46:18 +00:00
99a18ea03e Merge 5f9c6fb2a47d5626f915ef5ff0633ace50087b9e into 0abc6a2c25
0abc6a2c25 llama : llama_perf + option to disable timings during decode (#9355)
bd35cb0ae3 feat: remove a sampler from a chain (#9445)
Compare 3 commits »
root synced commits to refs/pull/3025/merge at root/llama.cpp from mirror 2024-09-13 00:36:17 +00:00
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
e665744317 llava : fix the script error in MobileVLM README (#9054)
d4c3c10fad lora : raise error if lm_head is ignored (#9103)
2a825116b6 cmake : fix for builds without GGML_CDEF_PUBLIC (#9338)
Compare 113 commits »
root synced commits to refs/pull/8354/merge at root/llama.cpp from mirror 2024-09-13 00:36:17 +00:00
e6b7801bd1 cann: Add host buffer type for Ascend NPU (#9406)
e665744317 llava : fix the script error in MobileVLM README (#9054)
d4c3c10fad lora : raise error if lm_head is ignored (#9103)
2a825116b6 cmake : fix for builds without GGML_CDEF_PUBLIC (#9338)
Compare 95 commits »