{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":612354784,"defaultBranch":"master","name":"llama.cpp","ownerLogin":"ggerganov","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2023-03-10T18:58:00.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/1991296?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1715991643.0","currentOid":""},"activityList":{"items":[{"before":"61e8a0adac3cf340bc0e90e25ec498e0bb4cc7fd","after":"f07e570c032b17c1a0a5a8ca6da7339929e83ea3","ref":"refs/heads/sl/fix-quant-near-zero","pushedAt":"2024-05-17T23:29:06.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"slaren","name":null,"path":"/slaren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2141330?s=80&v=4"},"commit":{"message":"use higher eps only for the quants that need it\n\nggml-ci","shortMessageHtmlLink":"use higher eps only for the quants that need it"}},{"before":"6b41894a025f63a79593a5c79b6423542f6cc54c","after":"61e8a0adac3cf340bc0e90e25ec498e0bb4cc7fd","ref":"refs/heads/sl/fix-quant-near-zero","pushedAt":"2024-05-17T23:25:58.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"slaren","name":null,"path":"/slaren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2141330?s=80&v=4"},"commit":{"message":"use higher eps only for the quants that need it\n\nggml-ci","shortMessageHtmlLink":"use higher eps only for the quants that need it"}},{"before":"f59edeeae9780a4384c61d926ce46f73072224f5","after":"6b41894a025f63a79593a5c79b6423542f6cc54c","ref":"refs/heads/sl/fix-quant-near-zero","pushedAt":"2024-05-17T23:16:01.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"slaren","name":null,"path":"/slaren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2141330?s=80&v=4"},"commit":{"message":"use higher eps only for the quants that need it\n\nggml-ci","shortMessageHtmlLink":"use higher eps only for the quants that need it"}},{"before":"0fc1e820a9900a3dd08ddd3c6abe6604c53b689b","after":"b43272afa29a64dcb8bcf26a96a05bac40792b92","ref":"refs/heads/master","pushedAt":"2024-05-17T23:09:13.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"jaime-m-p","name":null,"path":"/jaime-m-p","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167997752?s=80&v=4"},"commit":{"message":"Unicode codepoint flags for custom regexs (#7245)\n\n* Replace CODEPOINT_TYPE_* with codepoint_flags\r\n* Update and bugfix brute force random test\r\n* Deterministic brute force random test\r\n* Unicode normalization NFD\r\n* Get rid of BOM","shortMessageHtmlLink":"Unicode codepoint flags for custom regexs (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2291555524\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7245\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7245/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7245\">#7245</a>)"}},{"before":"82ca83db3c8d45df559c03a4225b6eb34808a2db","after":"0fc1e820a9900a3dd08ddd3c6abe6604c53b689b","ref":"refs/heads/master","pushedAt":"2024-05-17T16:54:52.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"JohannesGaessler","name":"Johannes Gäßler","path":"/JohannesGaessler","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/18492268?s=80&v=4"},"commit":{"message":"CUDA: faster large batch FA without tensor cores (#7314)","shortMessageHtmlLink":"CUDA: faster large batch FA without tensor cores (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2298918013\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7314\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7314/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7314\">#7314</a>)"}},{"before":"f4bd8b3d260bb09491ba63c77ab7012b744362ef","after":"82ca83db3c8d45df559c03a4225b6eb34808a2db","ref":"refs/heads/master","pushedAt":"2024-05-17T15:03:03.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"slaren","name":null,"path":"/slaren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2141330?s=80&v=4"},"commit":{"message":"ROCm: use native CMake HIP support (#5966)\n\nSupercedes #4024 and #4813.\r\n\r\nCMake's native HIP support has become the\r\nrecommended way to add HIP code into a project (see\r\n[here](https://rocm.docs.amd.com/en/docs-6.0.0/conceptual/cmake-packages.html#using-hip-in-cmake)).\r\nThis PR makes the following changes:\r\n\r\n1. The environment variable `HIPCXX` or CMake option\r\n`CMAKE_HIP_COMPILER` should be used to specify the HIP\r\ncompiler. Notably this shouldn't be `hipcc`, but ROCm's clang,\r\nwhich usually resides in `$ROCM_PATH/llvm/bin/clang`. Previously\r\nthis was control by `CMAKE_C_COMPILER` and `CMAKE_CXX_COMPILER`.\r\nNote that since native CMake HIP support is not yet available on\r\nWindows, on Windows we fall back to the old behavior.\r\n\r\n2. CMake option `CMAKE_HIP_ARCHITECTURES` is used to control the\r\nGPU architectures to build for. Previously this was controled by\r\n`GPU_TARGETS`.\r\n\r\n3. Updated the Nix recipe to account for these new changes.\r\n\r\n4. The GPU targets to build against in the Nix recipe is now\r\nconsistent with the supported GPU targets in nixpkgs.\r\n\r\n5. Added CI checks for HIP on both Linux and Windows. On Linux, we test\r\nboth the new and old behavior.\r\n\r\nThe most important part about this PR is the separation of the\r\nHIP compiler and the C/C++ compiler. This allows users to choose\r\na different C/C++ compiler if desired, compared to the current\r\nsituation where when building for ROCm support, everything must be\r\ncompiled with ROCm's clang.\r\n\r\n~~Makefile is unchanged. Please let me know if we want to be\r\nconsistent on variables' naming because Makefile still uses\r\n`GPU_TARGETS` to control architectures to build for, but I feel\r\nlike setting `CMAKE_HIP_ARCHITECTURES` is a bit awkward when you're\r\ncalling `make`.~~ Makefile used `GPU_TARGETS` but the README says\r\nto use `AMDGPU_TARGETS`. For consistency with CMake, all usage of\r\n`GPU_TARGETS` in Makefile has been updated to `AMDGPU_TARGETS`.\r\n\r\nThanks to the suggestion of @jin-eld, to maintain backwards\r\ncompatibility (and not break too many downstream users' builds), if\r\n`CMAKE_CXX_COMPILER` ends with `hipcc`, then we still compile using\r\nthe original behavior and emit a warning that recommends switching\r\nto the new HIP support. Similarly, if `AMDGPU_TARGETS` is set but\r\n`CMAKE_HIP_ARCHITECTURES` is not, then we forward `AMDGPU_TARGETS`\r\nto `CMAKE_HIP_ARCHITECTURES` to ease the transition to the new\r\nHIP support.\r\n\r\nSigned-off-by: Gavin Zhao <git@gzgz.dev>","shortMessageHtmlLink":"ROCm: use native CMake HIP support (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2177322787\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/5966\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/5966/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/5966\">#5966</a>)"}},{"before":"51e9d02599336e62948d29f1d6c05addeb921ac2","after":"f4bd8b3d260bb09491ba63c77ab7012b744362ef","ref":"refs/heads/master","pushedAt":"2024-05-17T14:25:44.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"rgerganov","name":"Radoslav Gerganov","path":"/rgerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/271616?s=80&v=4"},"commit":{"message":"rpc : set SO_REUSEADDR for the server socket (#7320)\n\nref: #7293","shortMessageHtmlLink":"rpc : set SO_REUSEADDR for the server socket (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2299954423\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7320\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7320/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7320\">#7320</a>)"}},{"before":null,"after":"2117b3038050c07a443770b7f086c9681030ddbe","ref":"refs/heads/ci-android","pushedAt":"2024-05-17T12:48:22.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"ggml : disable SIMD exp and silu for 32-bit ARM\n\nggml-ci","shortMessageHtmlLink":"ggml : disable SIMD exp and silu for 32-bit ARM"}},{"before":"d273c1402b25086fd91aef2467ac13f2e49fa0ea","after":"51e9d02599336e62948d29f1d6c05addeb921ac2","ref":"refs/heads/master","pushedAt":"2024-05-17T12:40:14.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"Added a single test function script and fix debug-test.sh to be more robust (#7279)\n\n* run-single-test.sh: added a single test function script and fix debug-test.sh to be more robust\r\n\r\n* debug-test.sh: combined execute and gdb test mode via -g flag\r\n\r\n* debug-test.sh: refactor\r\n\r\n* debug-test: refactor for clarity\r\n\r\n* debug-test.sh: comment style changes\r\n\r\n* debug-test.sh: fix gdb","shortMessageHtmlLink":"Added a single test function script and fix debug-test.sh to be more …"}},{"before":"27b040691cbe45314147c2745e891a38e9c048d4","after":"d273c1402b25086fd91aef2467ac13f2e49fa0ea","ref":"refs/heads/master","pushedAt":"2024-05-17T12:11:45.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"py : convert-hf-to-gguf-update improvements (#7340)\n\n* convert-hf-to-gguf-update: automate updating\r\n\r\n* convert-hf-to-gguf-update: improve download\r\n\r\n* share requests session for performance\r\n* create directories only when needed, don't skip downloads when empty directory encountered\r\n* be more graceful about errors","shortMessageHtmlLink":"py : convert-hf-to-gguf-update improvements (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2302467030\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7340\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7340/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7340\">#7340</a>)"}},{"before":"29c60d8cddcfd14fa8a6bf023a6c4eb8692c76ba","after":"27b040691cbe45314147c2745e891a38e9c048d4","ref":"refs/heads/master","pushedAt":"2024-05-17T11:24:38.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"llama : use n_embd_head_v when reshaping kqv (#7327)\n\n* llama : use n_embd_head_v instead of n_embd_head_k when reshaping kqv\r\n\r\n* llama : use n_embd_v_gqa and n_embd_head_v instead of n_embd_k_gqa and n_embd_head_k when making a view of cached value vectors.\r\n\r\n---------\r\n\r\nCo-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>","shortMessageHtmlLink":"llama : use n_embd_head_v when reshaping kqv (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2300291956\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7327\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7327/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7327\">#7327</a>)"}},{"before":null,"after":"6b2f496409330259da5fe9361ece56010a4664a7","ref":"refs/heads/gg/test-embd","pushedAt":"2024-05-17T11:01:17.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"wip","shortMessageHtmlLink":"wip"}},{"before":"359cbe3f46c90ce6f5151005e411b8fb74f8139e","after":"29c60d8cddcfd14fa8a6bf023a6c4eb8692c76ba","ref":"refs/heads/master","pushedAt":"2024-05-17T07:59:57.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"JohannesGaessler","name":"Johannes Gäßler","path":"/JohannesGaessler","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/18492268?s=80&v=4"},"commit":{"message":"tokenization: add warning for double BOS (#7332)","shortMessageHtmlLink":"tokenization: add warning for double BOS (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2300765527\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7332\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7332/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7332\">#7332</a>)"}},{"before":"e18bc6aaf3b547890609ed254ee5248e720e5840","after":"359cbe3f46c90ce6f5151005e411b8fb74f8139e","ref":"refs/heads/master","pushedAt":"2024-05-17T07:08:50.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"ggml-quants, llama : removed excess checks (#7274)","shortMessageHtmlLink":"ggml-quants, llama : removed excess checks (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2294213530\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7274\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7274/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7274\">#7274</a>)"}},{"before":"ee94172d33399d2e814ca05c8a3ff8c523ebb093","after":"e18bc6aaf3b547890609ed254ee5248e720e5840","ref":"refs/heads/master","pushedAt":"2024-05-17T07:01:58.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"convert : fix Qwen/Qwen-7b conversion (#7308)","shortMessageHtmlLink":"convert : fix Qwen/Qwen-7b conversion (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2298441942\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7308\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7308/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7308\">#7308</a>)"}},{"before":"934266c0e0b2aa9781fdba2deb112c161ff038a9","after":"ee94172d33399d2e814ca05c8a3ff8c523ebb093","ref":"refs/heads/master","pushedAt":"2024-05-17T07:00:17.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"server : add support for the RPC backend (#7305)\n\nref: #7292","shortMessageHtmlLink":"server : add support for the RPC backend (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2297890274\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7305\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7305/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7305\">#7305</a>)"}},{"before":"9c4fdcbec8c7fcc428e723b0d8a1cf1f351ba642","after":"934266c0e0b2aa9781fdba2deb112c161ff038a9","ref":"refs/heads/master","pushedAt":"2024-05-17T06:58:52.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"ggml : rewrite silu and softmax for cpu (#7154)\n\nThis change upstreams llamafile's vectorized expf() functions. This lets\r\nus compute softmax and silu more accurately than the short[65536] lookup\r\ntable that GGML previously used to make this operation go faster. We can\r\nsupport aarch64 and sse2+ with the worst case rounding error of 2ulp. It\r\nmakes make -j8 tests && ./tests/test-backend-ops -o SOFT_MAX -b CPU perf\r\ngo 1.5x faster for SSE2+FMA, 1.9x faster for AVX2+FMA and 2.1x on AVX512","shortMessageHtmlLink":"ggml : rewrite silu and softmax for cpu (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2286683454\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7154\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7154/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7154\">#7154</a>)"}},{"before":"24ecb58168dce81646c2ed425690a106591c8c6d","after":"9c4fdcbec8c7fcc428e723b0d8a1cf1f351ba642","ref":"refs/heads/master","pushedAt":"2024-05-17T00:11:03.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"[Server] Added --verbose option to README [no ci] (#7335)","shortMessageHtmlLink":"[Server] Added --verbose option to README [no ci] (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2301312883\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7335\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7335/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7335\">#7335</a>)"}},{"before":"e7f7bef2db07468bac9511162e1244dc4885fd43","after":null,"ref":"refs/heads/revert-7284-server-bench-fix-wait","pushedAt":"2024-05-16T18:43:53.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"phymbert","name":"Pierrick Hymbert","path":"/phymbert","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5741141?s=80&v=4"}},{"before":"9afdffe70ebf3166d429b4434783bb0b7f97bdeb","after":"24ecb58168dce81646c2ed425690a106591c8c6d","ref":"refs/heads/master","pushedAt":"2024-05-16T18:43:46.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"phymbert","name":"Pierrick Hymbert","path":"/phymbert","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5741141?s=80&v=4"},"commit":{"message":"Revert \"server bench: fix bench not waiting for model load (#7284)\" (#7334)\n\nThis reverts commit 583fd6b000ec9ad1b465b5c98524f4a0ae388077.","shortMessageHtmlLink":"Revert \"server bench: fix bench not waiting for model load (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2295484054\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7284\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7284/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7284\">#7284</a>)\" (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2301038080\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7334\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7334/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7334\">#…</a>"}},{"before":null,"after":"e7f7bef2db07468bac9511162e1244dc4885fd43","ref":"refs/heads/revert-7284-server-bench-fix-wait","pushedAt":"2024-05-16T18:09:10.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"phymbert","name":"Pierrick Hymbert","path":"/phymbert","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5741141?s=80&v=4"},"commit":{"message":"Revert \"server bench: fix bench not waiting for model load (#7284)\"\n\nThis reverts commit 583fd6b000ec9ad1b465b5c98524f4a0ae388077.","shortMessageHtmlLink":"Revert \"server bench: fix bench not waiting for model load (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2295484054\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7284\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7284/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7284\">#7284</a>)\""}},{"before":null,"after":"a085a8323aef383674759b777d3d5e02e56306a4","ref":"refs/heads/gg/test-bench","pushedAt":"2024-05-16T11:46:06.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ggerganov","name":"Georgi Gerganov","path":"/ggerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1991296?s=80&v=4"},"commit":{"message":"tmp","shortMessageHtmlLink":"tmp"}},{"before":"3b3963c55c8332e33533c44b2aa882b0e45f8292","after":"9afdffe70ebf3166d429b4434783bb0b7f97bdeb","ref":"refs/heads/master","pushedAt":"2024-05-16T09:04:08.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"rgerganov","name":"Radoslav Gerganov","path":"/rgerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/271616?s=80&v=4"},"commit":{"message":"rpc : get available mem for the CPU backend\n\nThis can be overridden with the -m command line option\n\nref: #7293","shortMessageHtmlLink":"rpc : get available mem for the CPU backend"}},{"before":"09e3a9ea20df85e37be857e426ed35e34d9fbb0e","after":"4b561bd7e1d19130f58f858c1f4085e0e31800c4","ref":"refs/heads/sycl-refactor","pushedAt":"2024-05-16T08:54:06.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"airMeng","name":"Meng, Hengyu","path":"/airMeng","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/39229107?s=80&v=4"},"commit":{"message":"backup","shortMessageHtmlLink":"backup"}},{"before":"dda64fc17c97820ea9489eb0cc9ae8b8fdce4926","after":"3b3963c55c8332e33533c44b2aa882b0e45f8292","ref":"refs/heads/master","pushedAt":"2024-05-16T06:58:30.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"rgerganov","name":"Radoslav Gerganov","path":"/rgerganov","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/271616?s=80&v=4"},"commit":{"message":"rpc : add command line arg for specifying backend memory\n\nref: #7293","shortMessageHtmlLink":"rpc : add command line arg for specifying backend memory"}},{"before":"0350f5815218c483fb3026a86adc44a115481625","after":"dda64fc17c97820ea9489eb0cc9ae8b8fdce4926","ref":"refs/heads/master","pushedAt":"2024-05-16T06:15:23.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"convert : get general.name from model dir, not its parent (#5615)\n\nCo-authored-by: Brian <mofosyne@gmail.com>","shortMessageHtmlLink":"convert : get general.name from model dir, not its parent (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2145023564\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/5615\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/5615/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/5615\">#5615</a>)"}},{"before":"ad52d5c259344888b06fd5acd3344c663dd0621d","after":"0350f5815218c483fb3026a86adc44a115481625","ref":"refs/heads/master","pushedAt":"2024-05-16T06:14:24.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"grammar, json, llama: replace push on emplace if it possible (#7273)","shortMessageHtmlLink":"grammar, json, llama: replace push on emplace if it possible (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2294186333\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7273\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7273/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7273\">#7273</a>)"}},{"before":"172b78210aae0e54d3668c5de14200efab9fac23","after":"ad52d5c259344888b06fd5acd3344c663dd0621d","ref":"refs/heads/master","pushedAt":"2024-05-16T05:38:43.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"doc: add references to hugging face GGUF-my-repo quantisation web tool. (#7288)\n\n* chore: add references to the quantisation space.\r\n\r\n* fix grammer lol.\r\n\r\n* Update README.md\r\n\r\nCo-authored-by: Julien Chaumond <julien@huggingface.co>\r\n\r\n* Update README.md\r\n\r\nCo-authored-by: Georgi Gerganov <ggerganov@gmail.com>\r\n\r\n---------\r\n\r\nCo-authored-by: Julien Chaumond <julien@huggingface.co>\r\nCo-authored-by: Georgi Gerganov <ggerganov@gmail.com>","shortMessageHtmlLink":"doc: add references to hugging face GGUF-my-repo quantisation web too…"}},{"before":"13ad16af1231ab2d245d35df3295bcfa23de1305","after":"172b78210aae0e54d3668c5de14200efab9fac23","ref":"refs/heads/master","pushedAt":"2024-05-16T05:36:43.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"ci: fix bin/Release path for windows-arm64 builds (#7317)\n\nSwitch to Ninja Multi-Config CMake generator to resurect bin/Release path\r\nthat broke artifact packaging in CI.","shortMessageHtmlLink":"ci: fix bin/Release path for windows-arm64 builds (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2299360488\" data-permission-text=\"Title is private\" data-url=\"https://github.com/ggerganov/llama.cpp/issues/7317\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/ggerganov/llama.cpp/pull/7317/hovercard\" href=\"https://github.com/ggerganov/llama.cpp/pull/7317\">#7317</a>)"}},{"before":"8f7080bf48828b538bc9387c3d150bbd4fb4cf2d","after":"13ad16af1231ab2d245d35df3295bcfa23de1305","ref":"refs/heads/master","pushedAt":"2024-05-16T02:47:36.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mofosyne","name":"Brian","path":"/mofosyne","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/827793?s=80&v=4"},"commit":{"message":"Add support for properly optimized Windows ARM64 builds with LLVM and MSVC (#7191)\n\n* logging: add proper checks for clang to avoid errors and warnings with VA_ARGS\r\n\r\n* build: add CMake Presets and toolchian files for Windows ARM64\r\n\r\n* matmul-int8: enable matmul-int8 with MSVC and fix Clang warnings\r\n\r\n* ci: add support for optimized Windows ARM64 builds with MSVC and LLVM\r\n\r\n* matmul-int8: fixed typos in q8_0_q8_0 matmuls\r\n\r\nCo-authored-by: Georgi Gerganov <ggerganov@gmail.com>\r\n\r\n* matmul-int8: remove unnecessary casts in q8_0_q8_0\r\n\r\n---------\r\n\r\nCo-authored-by: Georgi Gerganov <ggerganov@gmail.com>","shortMessageHtmlLink":"Add support for properly optimized Windows ARM64 builds with LLVM and…"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAETVvf7AA","startCursor":null,"endCursor":null}},"title":"Activity · ggerganov/llama.cpp"}