HappyZ happyz
happyz synced commits to refs/pull/3273/merge at happyz/memos from mirror 2024-05-29 18:19:20 -07:00
98f2cf6397 chore: tweak linter
b1cc1255bb chore: tweak seed data
b215426623 chore: update general setting
423861d48c fix: create idp in postgres
Compare 8 commits »
happyz synced new reference test_636997257 to happyz/gemma.cpp from mirror 2024-05-29 06:19:50 -07:00
happyz synced commits to test_636997257 at happyz/gemma.cpp from mirror 2024-05-29 06:19:50 -07:00
happyz synced commits to refs/pull/7596/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:48 -07:00
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
2ab977282b sync : ggml
Compare 9 commits »
happyz synced commits to refs/tags/b3030 at happyz/llama.cpp from mirror 2024-05-29 06:19:48 -07:00
happyz synced new reference refs/tags/b3030 to happyz/llama.cpp from mirror 2024-05-29 06:19:48 -07:00
happyz synced commits to refs/pull/7599/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:48 -07:00
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 9 commits »
happyz synced commits to refs/pull/7582/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:48 -07:00
3f62b146fd Merge 243b5efe0586c1e6fff749fbb52981e01d557bc7 into cce3dcffc5
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 10 commits »
happyz synced commits to refs/pull/7581/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:47 -07:00
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 10 commits »
happyz synced commits to refs/pull/7576/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:47 -07:00
0e8d8bfd6c Add Arc A750 and Arch linux to readme-sycl.md as verified GPU model and Linux distro (#7605)
504f0c340f ggml : fix typo in ggml.c (#7603)
Compare 3 commits »
happyz synced commits to refs/pull/7582/head at happyz/llama.cpp from mirror 2024-05-29 06:19:47 -07:00
243b5efe05 vulkan: select only one device for single gpu with multiple drivers
b864b50ce5 [SYCL] Align GEMM dispatch (#7566)
02c1ecad07 Tokenizer WPM fixes (#7500)
6bd12ce409 sycl : fix assert (#7563)
5442939fcc llama : support small Granite models (#7481)
Compare 16 commits »
happyz synced commits to refs/pull/7581/head at happyz/llama.cpp from mirror 2024-05-29 06:19:47 -07:00
200c39cc6b batched : make n_threads and n_threads_batch configurable in batched & batched-bench
504f0c340f ggml : fix typo in ggml.c (#7603)
b864b50ce5 [SYCL] Align GEMM dispatch (#7566)
02c1ecad07 Tokenizer WPM fixes (#7500)
6bd12ce409 sycl : fix assert (#7563)
Compare 17 commits »
happyz synced commits to refs/pull/7570/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:46 -07:00
0e8d8bfd6c Add Arc A750 and Arch linux to readme-sycl.md as verified GPU model and Linux distro (#7605)
504f0c340f ggml : fix typo in ggml.c (#7603)
b864b50ce5 [SYCL] Align GEMM dispatch (#7566)
Compare 4 commits »
happyz synced commits to refs/pull/7568/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:46 -07:00
0ece2cb013 Merge 4f64f7ebb018994b9e29ea7fabffbcbdda20a420 into cce3dcffc5
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 10 commits »
happyz synced commits to refs/pull/7555/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:46 -07:00
0e8d8bfd6c Add Arc A750 and Arch linux to readme-sycl.md as verified GPU model and Linux distro (#7605)
504f0c340f ggml : fix typo in ggml.c (#7603)
b864b50ce5 [SYCL] Align GEMM dispatch (#7566)
02c1ecad07 Tokenizer WPM fixes (#7500)
Compare 10 commits »
happyz synced commits to refs/pull/7553/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:46 -07:00
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 9 commits »
happyz synced commits to refs/pull/7551/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:46 -07:00
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 10 commits »
happyz synced commits to refs/pull/7548/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:45 -07:00
1d9a287ba9 Merge 0dda3c1028634d5f392a7838aa7043a16f2d7048 into cce3dcffc5
cce3dcffc5 cuda : non-cont concat support (#7610)
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
00281b7be3 scripts : remove mpi remnants
Compare 10 commits »
happyz synced commits to refs/pull/7527/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:45 -07:00
cce3dcffc5 cuda : non-cont concat support (#7610)
84d9277fe2 split fattn compile via extern templates
210d99173d llama-bench : add support for the RPC backend (#7435)
87bdf2a199 ggml : use atomic_flag for critical section (#7598)
Compare 10 commits »
happyz synced commits to refs/pull/7535/merge at happyz/llama.cpp from mirror 2024-05-29 06:19:45 -07:00
0e8d8bfd6c Add Arc A750 and Arch linux to readme-sycl.md as verified GPU model and Linux distro (#7605)
504f0c340f ggml : fix typo in ggml.c (#7603)
Compare 3 commits »