HappyZ happyz
happyz synced commits to refs/pull/6848/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
261d3dbad9 Opacity action trigger.
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
Compare 10 commits »
happyz synced commits to refs/pull/6866/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
Compare 10 commits »
happyz synced commits to refs/pull/6858/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
9ec1350555 Merge c27bcb0235d4fb4d6923a173116e304d5236481b into 928e0b7013
928e0b7013 Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
0c4d489e29 quantize: add imatrix and dataset metadata in GGUF (#6658)
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
Compare 13 commits »
happyz synced commits to refs/pull/6848/head at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
261d3dbad9 Opacity action trigger.
happyz synced commits to refs/pull/6869/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
cd87836c27 Merge cf9dca34cbd02c89fb3f3c46e85da817fe89744b into 017e6999b5
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
cf9dca34cb enable UT of QNN backend works fine with test-backend-ops.cpp
Compare 12 commits »
happyz synced commits to refs/pull/6869/head at happyz/llama.cpp from mirror 2024-04-26 11:14:02 -07:00
cf9dca34cb enable UT of QNN backend works fine with test-backend-ops.cpp
happyz synced commits to refs/pull/6832/head at happyz/llama.cpp from mirror 2024-04-26 11:14:01 -07:00
f7d2c0a5cd Added set thread affinity for Linux
a3e75fe481 Fixes
Compare 2 commits »
happyz synced commits to refs/pull/6834/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:01 -07:00
1389794116 Merge aa66db1cb7083aed883e2ae9460becb296603dd1 into 017e6999b5
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
Compare 11 commits »
happyz synced commits to refs/pull/6840/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:01 -07:00
b6f07f64e8 Merge c34c47237148ba264a4d1ac75d1ecc70c7952589 into 928e0b7013
928e0b7013 Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
0c4d489e29 quantize: add imatrix and dataset metadata in GGUF (#6658)
017e6999b5 add basic tensor data validation function (#6884)
c34c472371 llamafile : improve moe prompt eval speed on cpu
Compare 14 commits »
happyz synced commits to refs/pull/6840/head at happyz/llama.cpp from mirror 2024-04-26 11:14:01 -07:00
c34c472371 llamafile : improve moe prompt eval speed on cpu
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
9e4e077ec5 ci: server: fix python installation (#6922)
Compare 21 commits »
happyz synced commits to refs/pull/6839/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:01 -07:00
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
9e4e077ec5 ci: server: fix python installation (#6922)
83b72cb086 Merge pull request from GHSA-p5mv-gjc5-mwqv
Compare 8 commits »
happyz synced commits to refs/pull/6829/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:00 -07:00
1d8717aa77 Merge 2ef868d9cdc8ba85a39719c318a57dfddec0142b into e2764cd7ca
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
Compare 10 commits »
happyz synced commits to refs/pull/6828/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:00 -07:00
83093968ef Merge 244508af0f9b811722ca439a6753619f3d4786ed into 017e6999b5
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
Compare 11 commits »
happyz synced commits to refs/pull/6826/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:00 -07:00
928e0b7013 Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
0c4d489e29 quantize: add imatrix and dataset metadata in GGUF (#6658)
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
Compare 15 commits »
happyz synced commits to refs/pull/6822/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:00 -07:00
928e0b7013 Reset schedule earlier to allow overlap with ggml graph computation on device (#6933)
0c4d489e29 quantize: add imatrix and dataset metadata in GGUF (#6658)
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
Compare 13 commits »
happyz synced commits to refs/pull/6831/merge at happyz/llama.cpp from mirror 2024-04-26 11:14:00 -07:00
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
Compare 11 commits »
happyz synced commits to refs/pull/6810/merge at happyz/llama.cpp from mirror 2024-04-26 11:13:59 -07:00
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
9e4e077ec5 ci: server: fix python installation (#6922)
83b72cb086 Merge pull request from GHSA-p5mv-gjc5-mwqv
Compare 8 commits »
happyz synced commits to refs/pull/6784/merge at happyz/llama.cpp from mirror 2024-04-26 11:13:59 -07:00
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
9e4e077ec5 ci: server: fix python installation (#6922)
Compare 9 commits »
happyz synced commits to refs/pull/6778/merge at happyz/llama.cpp from mirror 2024-04-26 11:13:59 -07:00
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
7f5ff558ee server: stop generation at `n_ctx_train` if `n_predict` is not set (#6638)
Compare 10 commits »
happyz synced commits to refs/pull/6766/merge at happyz/llama.cpp from mirror 2024-04-26 11:13:59 -07:00
017e6999b5 add basic tensor data validation function (#6884)
e2764cd7ca gguf : fix mismatch between alloc and free functions (#6929)
4b1c3c98b4 llamafile : use 64-bit integers in sgemm (#6928)
bbe3c6e761 ci: server: fix python installation (#6925)
Compare 11 commits »