nwpie
1 Followers · 0 Following
  • Joined on 2024-06-23
Repositories
3
 Projects Packages Public Activity Starred Repositories
nwpie synced and deleted reference refs/tags/refs/pull/8311/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
nwpie synced and deleted reference refs/tags/refs/pull/8314/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
nwpie synced commits to master at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
7ed03b8974 llama : fix compile warning (#8304)
1d894a790e cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
Compare 10 commits »
nwpie synced commits to refs/pull/6035/head at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
34f957fd19 speedup 10x
28b97e8841 [CANN] Add Ascend NPU backend
Compare 2 commits »
nwpie synced commits to refs/pull/6035/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
3928826bc2 Merge 34f957fd193d2ed9fdc330c6d5f4b003132411cf into 1f3e1b66e2
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
34f957fd19 speedup 10x
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
Compare 11 commits »
nwpie synced commits to refs/pull/6080/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
e609b8199b Merge 64472c9e97 into 148ec970b6
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 130 commits »
nwpie synced commits to refs/pull/7187/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
cf11fa1f51 Merge ffca1bb5fbbae893ca9fb8b6262036bf582eab32 into 7ed03b8974
7ed03b8974 llama : fix compile warning (#8304)
1d894a790e cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
148ec970b6 convert : remove AWQ remnants (#8320)
Compare 17 commits »
nwpie synced commits to refs/pull/8035/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
852bd4b050 Merge c0ba35740cd9d75ffe841d0855fc0a93e1d1359f into 148ec970b6
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 14 commits »
nwpie synced commits to refs/pull/8039/head at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
0137683e11 style: spaces
nwpie synced commits to refs/pull/8039/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
82f73befe3 Merge 0137683e11 into 1f3e1b66e2
0137683e11 style: spaces
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
Compare 15 commits »
nwpie synced commits to refs/pull/8048/head at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
5360799e85 llama-gguf-hash: add sha256
ccc6ef7b3c llama-gguf-hash: makefile sha1 and xxhash moved to it's own obj file
Compare 2 commits »
nwpie synced commits to refs/pull/8048/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
0882c9b6ec Merge 5360799e85 into 1f3e1b66e2
5360799e85 llama-gguf-hash: add sha256
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
ccc6ef7b3c llama-gguf-hash: makefile sha1 and xxhash moved to it's own obj file
148ec970b6 convert : remove AWQ remnants (#8320)
Compare 17 commits »
nwpie synced commits to refs/pull/8119/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
f820589e7b Merge 613a3c6a53 into 148ec970b6
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 13 commits »
nwpie synced commits to refs/pull/8187/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
e74af0a89f Merge 712e4d9450 into 148ec970b6
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 14 commits »
nwpie synced commits to refs/pull/8196/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
be58422677 Merge 2727b02b4d into 1f3e1b66e2
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
Compare 17 commits »
nwpie synced commits to refs/pull/8208/head at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
1e2baaf30f add typedef of WIN32_MEMORY_RANGE_ENTRY and PWIN32_MEMORY_RANGE_ENTRY to make it work under MinGW
0c6ddf46f0 0x601 not works, use _WIN32_WINNT_WIN7 instead
c8cab643bc correct _WIN32_WINNT and WINVER settings
Compare 3 commits »
nwpie synced commits to refs/pull/8208/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
9112207454 Merge 1e2baaf30f452407c960056781360baca1a5aec4 into 1f3e1b66e2
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
1e2baaf30f add typedef of WIN32_MEMORY_RANGE_ENTRY and PWIN32_MEMORY_RANGE_ENTRY to make it work under MinGW
0c6ddf46f0 0x601 not works, use _WIN32_WINNT_WIN7 instead
c8cab643bc correct _WIN32_WINNT and WINVER settings
Compare 18 commits »
nwpie synced commits to refs/pull/8236/head at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
ab4b1a7553 Merge branch 'master' into mixed_types_gemm
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 38 commits »
nwpie synced commits to refs/pull/8268/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
04121d56af Merge b25654dde1 into 148ec970b6
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
8e558309dc CUDA: MMQ support for iq4_nl, iq4_xs (#8278)
0a423800ff CUDA: revert part of the RDNA1 optimizations (#8309)
Compare 13 commits »
nwpie synced commits to refs/pull/8279/merge at nwpie/llama.cpp from mirror 2024-07-05 17:33:37 +03:00
3998e01991 Merge 3c5acd512a into 1d894a790e
1d894a790e cmake : add GGML_BUILD and GGML_SHARED macro definitions (#8281)
1f3e1b66e2 Enabled more data types for oneMKL gemm_batch (#8236)
148ec970b6 convert : remove AWQ remnants (#8320)
2cccbaa008 llama : minor indentation during tensor loading (#8304)
Compare 10 commits »