cc473cac7cea1484c1f870231073b0bf0352c6f9		branch 'master' of https://github.com/ggml-org/llama.cpp
fe9235d795d1cc69441db8c3ae5ce645bfa55a8f	not-for-merge	branch '0cc4m/vulkan-coopmat-amd-windows' of https://github.com/ggml-org/llama.cpp
c8ee1bccdd71564d0489dd1d53183db161e9ddd8	not-for-merge	branch '0cc4m/vulkan-fix-mm-tests' of https://github.com/ggml-org/llama.cpp
aa014d7e89a6191bf4924d995fa1487ed1cfaecf	not-for-merge	branch '0cc4m/vulkan-instance-cleanup' of https://github.com/ggml-org/llama.cpp
97c6d272c52f7291d467514ffa8387ceb22c51fc	not-for-merge	branch '0cc4m/vulkan-mmq-dp4a' of https://github.com/ggml-org/llama.cpp
9af90481d03e870adebc0a26cb8600682aacc518	not-for-merge	branch '0cc4m/vulkan-renderdoc' of https://github.com/ggml-org/llama.cpp
4f3a7e279b87d0b616fb149490f69ff74432b1e9	not-for-merge	branch '0cc4m/vulkan-subgroup-size-control-amd' of https://github.com/ggml-org/llama.cpp
dd14d818e040f5b96d214371f26362aa0030d7f4	not-for-merge	branch '7507-main-intel-dockerfile' of https://github.com/ggml-org/llama.cpp
cfbf33a7052d268266d53a55b8c4c6aca9cecde4	not-for-merge	branch 'SVE-vector-length-agnostic-VLA-gg' of https://github.com/ggml-org/llama.cpp
51f0bd50a1c276adfd85e6c7f7f3ce670683d540	not-for-merge	branch 'add-gemma2-soft-capping' of https://github.com/ggml-org/llama.cpp
ee7456926e636b5029456fcbbbede3da5bedf6f7	not-for-merge	branch 'alloc-assert-fix' of https://github.com/ggml-org/llama.cpp
de7e0912b6fdac6963f96565338b3bfd08a3d192	not-for-merge	branch 'apply-3585' of https://github.com/ggml-org/llama.cpp
bb39b87964838a6be0a71aeca3d9900f6cfdf524	not-for-merge	branch 'assert-restore-abort' of https://github.com/ggml-org/llama.cpp
78fafcaf1042080f745bc5591e921455059ab7af	not-for-merge	branch 'avoid-gnu-source' of https://github.com/ggml-org/llama.cpp
2fcdf869cd813c350c9e27f9118d81a723bea670	not-for-merge	branch 'batched-bench' of https://github.com/ggml-org/llama.cpp
30ac7a41171bc9df043dc00b62f81b2c61f9b9e0	not-for-merge	branch 'build-metal-default' of https://github.com/ggml-org/llama.cpp
72e7ef4e53a88f3c4a582f2881b307d2964ff831	not-for-merge	branch 'cam-simple-fix' of https://github.com/ggml-org/llama.cpp
7286b83d3f1b1df627ca25097d4d67cd604ed484	not-for-merge	branch 'ceb/bert' of https://github.com/ggml-org/llama.cpp
a37696d4f1bdd66aa4bc9f8a1b86ccfff725c603	not-for-merge	branch 'ceb/bert-tokenizer-fixes' of https://github.com/ggml-org/llama.cpp
0b673ca1879ceba8a9f669ba5d61c79a2aade522	not-for-merge	branch 'ceb/convert-hf-refactor' of https://github.com/ggml-org/llama.cpp
f8ab53919074619a21a7d77b2085e68b4e445f0d	not-for-merge	branch 'ceb/convert-vocab-fallback' of https://github.com/ggml-org/llama.cpp
b0547d2196557035b458ccacac973d6502229207	not-for-merge	branch 'ceb/fix-badspecial-silentfail' of https://github.com/ggml-org/llama.cpp
494f70f939bc9e97dcc1173f5c6b4fea75c974bd	not-for-merge	branch 'ceb/fix-cmake-typo' of https://github.com/ggml-org/llama.cpp
c8554b80beef6e901ef5370ed8059b03e11a1de9	not-for-merge	branch 'ceb/fix-cuda-warning-flags' of https://github.com/ggml-org/llama.cpp
7c87353e61dd7e00df7b6226e6753f922e3786cb	not-for-merge	branch 'ceb/fix-draft-model-default' of https://github.com/ggml-org/llama.cpp
1b05817112e1d7acee7c04a54ff0cb9ddb85e914	not-for-merge	branch 'ceb/fix-logit-check' of https://github.com/ggml-org/llama.cpp
32a392fe6878e40fd02c2ba0c72163b252e68b75	not-for-merge	branch 'ceb/fix-msvc-build' of https://github.com/ggml-org/llama.cpp
d05c13b3b91a867658732905f9ca7ce157b413ca	not-for-merge	branch 'ceb/fix-win-unicode-fpaths' of https://github.com/ggml-org/llama.cpp
f824902623c9145a299c1daad91d107ad9407bec	not-for-merge	branch 'ceb/fix-yarn-neox' of https://github.com/ggml-org/llama.cpp
5b74310e6efc6775cdbd94b2dd9898364b44aac4	not-for-merge	branch 'ceb/libstdcpp-assertions' of https://github.com/ggml-org/llama.cpp
ccd757a174771a5f8b7b153d383ca84d31e644d0	not-for-merge	branch 'ceb/nomic-bert' of https://github.com/ggml-org/llama.cpp
145321516506b9cfda00b62b669ac4fa639ecc5c	not-for-merge	branch 'ceb/nomic-vulkan-fix-add' of https://github.com/ggml-org/llama.cpp
6272b6764ad4b39eb05a411489577d3a6c914b89	not-for-merge	branch 'ceb/perf-faster-multigpu' of https://github.com/ggml-org/llama.cpp
4a3bc1522e92d8a6da506db5d97b4b4fdf2db6a7	not-for-merge	branch 'ceb/restore-convert' of https://github.com/ggml-org/llama.cpp
87a6088ffe1ad281258d70cfa6b6153af30f11d0	not-for-merge	branch 'ceb/wpm-portable-tolower' of https://github.com/ggml-org/llama.cpp
90a0349349d5f4093ad5a666de296cad6424dbc5	not-for-merge	branch 'cedo/add-outetts-v0.3' of https://github.com/ggml-org/llama.cpp
a1cdd29cd20a1c1fe7a7c33f77dbf38a4db90296	not-for-merge	branch 'chunks' of https://github.com/ggml-org/llama.cpp
007f2ece0a3e6ed45b02524c47540384e0fce0bc	not-for-merge	branch 'ci-android' of https://github.com/ggml-org/llama.cpp
eb0bf32caf721c2fecaac3b409ed6a7edc875659	not-for-merge	branch 'ci/server/fix-slow-test' of https://github.com/ggml-org/llama.cpp
31ff9e2e83c03404678376903e7e44b56c53c41e	not-for-merge	branch 'ci_cublas' of https://github.com/ggml-org/llama.cpp
a235b7c532bba6e5fd2f6d0c7215145800ed7c01	not-for-merge	branch 'codeplay/dequant_q4_K_improvements' of https://github.com/ggml-org/llama.cpp
ce6e28cc2385d72c386a86062dc9b3dd7fbbc035	not-for-merge	branch 'codeplay/fix-matmul-arith' of https://github.com/ggml-org/llama.cpp
18133cab40075e4cf8f953440a2d45fdfaf2a04e	not-for-merge	branch 'codeplay/revert-host-alloc' of https://github.com/ggml-org/llama.cpp
eab4a88210c026844f3756d50d24de5d5564c21b	not-for-merge	branch 'codeplay/sycl-main' of https://github.com/ggml-org/llama.cpp
712e4d94502189362e012db7eaa09ba457c189d4	not-for-merge	branch 'codeplay/tg-warmup' of https://github.com/ggml-org/llama.cpp
80626503438b28db65348635100d12883c9a517f	not-for-merge	branch 'compilade/batch-splits' of https://github.com/ggml-org/llama.cpp
75b3a09602d36838f69daeb0adab54797f878c02	not-for-merge	branch 'compilade/bitnet-ternary' of https://github.com/ggml-org/llama.cpp
c32d39cefb59333db5be8760e2533413bc016f59	not-for-merge	branch 'compilade/convert-hf-refactor' of https://github.com/ggml-org/llama.cpp
fbddb2625024b805f0e7d72d25b6d3a9a3aea9f3	not-for-merge	branch 'compilade/cuda-tq2_0' of https://github.com/ggml-org/llama.cpp
b971122eb1a10c0d1f1369ef425da027c894850c	not-for-merge	branch 'compilade/faster-lazy-safetensors' of https://github.com/ggml-org/llama.cpp
9329953a61215de3b0cc458c50e8e3b955ec10ad	not-for-merge	branch 'compilade/faster-session-sizes' of https://github.com/ggml-org/llama.cpp
64b7d858910e7056d36b113cb72512df274c34f1	not-for-merge	branch 'compilade/fix-command-r' of https://github.com/ggml-org/llama.cpp
50d1a035f0f8b35eeb850f5dc50fe68a8b39c55d	not-for-merge	branch 'compilade/fix-convert-gemma-1-instruct' of https://github.com/ggml-org/llama.cpp
1932a1b871e97e25496985bf4b3b53d3e7227a16	not-for-merge	branch 'compilade/fix-metadata-name-extraction' of https://github.com/ggml-org/llama.cpp
59ce85318aeace3d100395b86061fd10b3af6f54	not-for-merge	branch 'compilade/fix-mpt-pretok' of https://github.com/ggml-org/llama.cpp
f89eaa921e481fe6aeb7ead98d41af516d46496d	not-for-merge	branch 'compilade/fix-pydantic-example' of https://github.com/ggml-org/llama.cpp
93ec58b932ae132f1ce65d0a6d932466e2bd3818	not-for-merge	branch 'compilade/fix-server-long-system-prompt' of https://github.com/ggml-org/llama.cpp
9a424a3872b9d016e26427f249dbd4e13291c4d6	not-for-merge	branch 'compilade/fix-server-tests-penalty' of https://github.com/ggml-org/llama.cpp
73bc9350cd614adfdd4cdbcdac31c838d10af84a	not-for-merge	branch 'compilade/gguf-py-dequant' of https://github.com/ggml-org/llama.cpp
aaf7bc89e49b2bd632b701b4a98ad106872812d0	not-for-merge	branch 'compilade/gguf-py-fix-old-numpy' of https://github.com/ggml-org/llama.cpp
c5fe1d6cdce12fd7ec7a84dc954189999f1f4ae2	not-for-merge	branch 'compilade/gguf-py-fix-q-shape' of https://github.com/ggml-org/llama.cpp
229c35cb590b436947ac221a7ce5cb8da2b0eb2d	not-for-merge	branch 'compilade/gguf-py-quants-class' of https://github.com/ggml-org/llama.cpp
1be357d990c00e4f5aee853a2ff7ec58e254965f	not-for-merge	branch 'compilade/imatrix-batched-chunks' of https://github.com/ggml-org/llama.cpp
11f78c6a2d651e450330d1eee60de2415cac939f	not-for-merge	branch 'compilade/lazier-moe-convert-hf' of https://github.com/ggml-org/llama.cpp
e0af2df6902063b0fd2f93f71163af1c41efa7b2	not-for-merge	branch 'compilade/lazy-bfloat16-convert-hf' of https://github.com/ggml-org/llama.cpp
bffdaf401000770e3adfa80c4867ab452002dd04	not-for-merge	branch 'compilade/lazy-convert-hf' of https://github.com/ggml-org/llama.cpp
c9ecf620d6f12c628cadbf25644d06a97a67af27	not-for-merge	branch 'compilade/mamba2' of https://github.com/ggml-org/llama.cpp
faaac59d16c5adc366d26ef091f0510cf4b9b3ec	not-for-merge	branch 'compilade/nul-str-token' of https://github.com/ggml-org/llama.cpp
a34fc0dd86422c472aebb3a3a03450466c79bb96	not-for-merge	branch 'compilade/pyright-fix-ignores' of https://github.com/ggml-org/llama.cpp
86ccd30983baffe90e38ecf7ab2fa9fda659cfc8	not-for-merge	branch 'compilade/pyright-tests' of https://github.com/ggml-org/llama.cpp
65a1a5856286d95d56da8497256176d74185a968	not-for-merge	branch 'compilade/q8_0-convert-hf' of https://github.com/ggml-org/llama.cpp
375de5b1f8c07b5bfdef7f00b738eb176f8431ba	not-for-merge	branch 'compilade/refactor-kv-cache' of https://github.com/ggml-org/llama.cpp
ddc59e8e0a7d4c138d8b0d3d2db8efb0f6e9abab	not-for-merge	branch 'compilade/refactor-kv-cache-gg' of https://github.com/ggml-org/llama.cpp
9cddd9aeecdbb1c7f191b930a6acd598ae627556	not-for-merge	branch 'compilade/refactor-session-files' of https://github.com/ggml-org/llama.cpp
a44f22e7d3f5228aa01dd89db2ffbcccc39a35f6	not-for-merge	branch 'compilade/requirements-cpu-torch' of https://github.com/ggml-org/llama.cpp
ba06b2deb78001875215f9fe2e5f8dbc95737e0b	not-for-merge	branch 'compilade/tokenize-example-parse-special' of https://github.com/ggml-org/llama.cpp
d798a17c34f2326093d0cf2c0ea90b8fded15dc6	not-for-merge	branch 'cuda-batched-gemm' of https://github.com/ggml-org/llama.cpp
6966474928233a0e2767a83a1f7e9a4cd314f169	not-for-merge	branch 'cuda-batched-gemm-deq' of https://github.com/ggml-org/llama.cpp
4cc78d38736a582e005ed00bbb19479d68008891	not-for-merge	branch 'cuda-cublas-opts' of https://github.com/ggml-org/llama.cpp
cd3e20fb50d73080dd6d72ad68e401cc42cd53cf	not-for-merge	branch 'cuda-multi-gpu' of https://github.com/ggml-org/llama.cpp
49af767fadfc44dd079d49038089b4ee99d77e0c	not-for-merge	branch 'cuda-quantum-batch' of https://github.com/ggml-org/llama.cpp
c5650ed470f6264046431c8b5e43cbfe3e680d17	not-for-merge	branch 'custom-attention-mask' of https://github.com/ggml-org/llama.cpp
784d14ed31dc6146ec0a07f3d48416af2d7917b6	not-for-merge	branch 'custom-attention-mask-no-roped-cache' of https://github.com/ggml-org/llama.cpp
dab42893c97f75bf9d87648a77c8486ee47dc7dd	not-for-merge	branch 'deploy' of https://github.com/ggml-org/llama.cpp
a3e6d6228338b8656db36bc314803bbb99eb77e2	not-for-merge	branch 'dequantize-matmul-3-gg' of https://github.com/ggml-org/llama.cpp
a169bb889cfe7b77a798f04fbc573e67ccb4316a	not-for-merge	branch 'dev' of https://github.com/ggml-org/llama.cpp
40ec4882c4d5cb67a9384a7eb7e38314360d8242	not-for-merge	branch 'f16c' of https://github.com/ggml-org/llama.cpp
703764a382689bd905803cfd851ae7942360248b	not-for-merge	branch 'fairydreaming/t5-clean-3-gg' of https://github.com/ggml-org/llama.cpp
e00c9d1c5e760c6b1d0f935fb80318d37b09cb46	not-for-merge	branch 'fall-back-to-jinja' of https://github.com/ggml-org/llama.cpp
284870c8686e1f8cee9871331675b5ef24031f74	not-for-merge	branch 'fix-convert-modelname' of https://github.com/ggml-org/llama.cpp
977629a34e6995f289ce11d25e5284b6a8e99c59	not-for-merge	branch 'fix-eos' of https://github.com/ggml-org/llama.cpp
ee268b544616a9d9d1fe4dc01fbfd86fc4f7e5a8	not-for-merge	branch 'fix-kv-cache-access' of https://github.com/ggml-org/llama.cpp
b979fc97ba58195b74f7b8c9481ebd7372fe626d	not-for-merge	branch 'fix-ninja-metallib-build' of https://github.com/ggml-org/llama.cpp
acead654d2b9528e8020f43a5162793b3434f777	not-for-merge	branch 'fix-refact' of https://github.com/ggml-org/llama.cpp
5418932b718033f12ec75cbdedf0be1d2c4deaf2	not-for-merge	branch 'fix-sessions' of https://github.com/ggml-org/llama.cpp
47d604fa2db4754d649f0b883ba3db030f842085	not-for-merge	branch 'fix-tensor-split-zero' of https://github.com/ggml-org/llama.cpp
20054a38c11c734a190820a62352d1131f0eae93	not-for-merge	branch 'fix_clblast' of https://github.com/ggml-org/llama.cpp
16dab13bdefa8a41c976321f526c8cb629333a95	not-for-merge	branch 'fix_cmd_name' of https://github.com/ggml-org/llama.cpp
a6a8f8d09c8e27a70926d8a52016ce8f49d954dd	not-for-merge	branch 'fix_ctx_default' of https://github.com/ggml-org/llama.cpp
4b1770109c358c58bfb3f471da5fbf3c8b9eafbe	not-for-merge	branch 'fix_q_xxs_mul_mat' of https://github.com/ggml-org/llama.cpp
c5d8bb5a81e947732e0cec429b495f38b0b85ef0	not-for-merge	branch 'fix_sycl_ci' of https://github.com/ggml-org/llama.cpp
36ddd129241386ce6edb745bb00f2377543e426a	not-for-merge	branch 'flash-attn' of https://github.com/ggml-org/llama.cpp
ac26f2702806744126b8edeb3d42dab1ce91cae1	not-for-merge	branch 'flash-attn-cuda' of https://github.com/ggml-org/llama.cpp
5dcccb3a7d0a6d1ce5886dd1f055555fd7759568	not-for-merge	branch 'gg/add-phi-3-support' of https://github.com/ggml-org/llama.cpp
9998ecd1912294be66c37b31805872274cb9f700	not-for-merge	branch 'gg/add-phixtral' of https://github.com/ggml-org/llama.cpp
57349e1db352aa941f336f0201d74b576368e551	not-for-merge	branch 'gg/allow-kv-overrides' of https://github.com/ggml-org/llama.cpp
072e0a4d3b8d2b583500fcd05c3f6cd8b7181575	not-for-merge	branch 'gg/authors' of https://github.com/ggml-org/llama.cpp
b5af7ad84fae422034179b18f55c6172f17fee2e	not-for-merge	branch 'gg/avoid-mutex' of https://github.com/ggml-org/llama.cpp
0ba20ed97ad8b68b9382ca719e1b0428653d6904	not-for-merge	branch 'gg/bert-f16' of https://github.com/ggml-org/llama.cpp
e9f2abfc8cf6561321bf916438d8080db81626a9	not-for-merge	branch 'gg/bitnet' of https://github.com/ggml-org/llama.cpp
80cb3127df55a05a7688797ae5b46be8c0b6a8cf	not-for-merge	branch 'gg/bpe-preprocess' of https://github.com/ggml-org/llama.cpp
ff4cb6ef4c6113a6f8de439298a89dba4c6540cc	not-for-merge	branch 'gg/build-linux-static' of https://github.com/ggml-org/llama.cpp
969b264657f12e42e1e3a2988bd790c8c2ee811a	not-for-merge	branch 'gg/build-pack-lib-include' of https://github.com/ggml-org/llama.cpp
8a8f8b953f6d21c2be62fb0e8f8c509d58b8c6ca	not-for-merge	branch 'gg/cache-token-to-piece' of https://github.com/ggml-org/llama.cpp
cc1c017191b70f6f888fb3c6730ee8a3f0dba595	not-for-merge	branch 'gg/cb-naming' of https://github.com/ggml-org/llama.cpp
4356325ef5ee77f0ce9eb2f75471ee995be516b8	not-for-merge	branch 'gg/check-python-version' of https://github.com/ggml-org/llama.cpp
77c16ee0d4ab8ec96c02005155c6a9e98280f0a8	not-for-merge	branch 'gg/ci-loongson' of https://github.com/ggml-org/llama.cpp
492eaad5717d2df7fd814e01c1a1c551f7001ca5	not-for-merge	branch 'gg/ci-python' of https://github.com/ggml-org/llama.cpp
fb8f142554315ac2311afda900ad0f00c2d48926	not-for-merge	branch 'gg/cmake-dedup-link' of https://github.com/ggml-org/llama.cpp
7e9208e4080f698dea6f4552196ae0987bd1f549	not-for-merge	branch 'gg/compare-change-path' of https://github.com/ggml-org/llama.cpp
adcf16fd685c6c9d336868667dd509592934fe2b	not-for-merge	branch 'gg/convert-fix-byte-tokens' of https://github.com/ggml-org/llama.cpp
4fbb801a9d512e2ede0e8e72a53af6a7695429cf	not-for-merge	branch 'gg/cpu-fix-cpy-iq' of https://github.com/ggml-org/llama.cpp
a40f6110f0868070d12f992ee263118536354f1f	not-for-merge	branch 'gg/cublas-f32' of https://github.com/ggml-org/llama.cpp
f02ea667c17912946868650cf5234b1e30e2e3f7	not-for-merge	branch 'gg/disable-sgemm' of https://github.com/ggml-org/llama.cpp
31f2d03f1bc1e88523d70d70a651ea095b8bd85b	not-for-merge	branch 'gg/enable-cb-default' of https://github.com/ggml-org/llama.cpp
ef79941ac9151bd5541e23e4e6328025df06c18e	not-for-merge	branch 'gg/fa-req-kq-hs' of https://github.com/ggml-org/llama.cpp
974e3cadff6aaedb0308d02fb0b7073f9dbed31b	not-for-merge	branch 'gg/fix-android' of https://github.com/ggml-org/llama.cpp
87f4102a70b54c002ad37f966717e4f13a94410a	not-for-merge	branch 'gg/fix-cpu-blas' of https://github.com/ggml-org/llama.cpp
65f9293d1418559838170c536def82e4d7c8def1	not-for-merge	branch 'gg/fix-devops' of https://github.com/ggml-org/llama.cpp
4ec0e9abbfcf47259da9489f8f16af694bb78a9b	not-for-merge	branch 'gg/fix-embeddings-wip' of https://github.com/ggml-org/llama.cpp
8c259f6f3edfb1261924a2b3490504cd1918d200	not-for-merge	branch 'gg/fix-min-max' of https://github.com/ggml-org/llama.cpp
117f7adbd9de97651a4c375e5fb34621fcc3f808	not-for-merge	branch 'gg/fix-python-names' of https://github.com/ggml-org/llama.cpp
23742deb5beb0e320bfb171545f595b8e60bccd5	not-for-merge	branch 'gg/fix-spm-added-tokens-dict-4958' of https://github.com/ggml-org/llama.cpp
9862d59c055a1cb35a9a92dc291fe589b30b67e3	not-for-merge	branch 'gg/fix-starcoder2' of https://github.com/ggml-org/llama.cpp
7216af5c09bdc6c68e6aa8d8fe78721f437726d4	not-for-merge	branch 'gg/fix-vld1q_s8_x4-4872' of https://github.com/ggml-org/llama.cpp
c240ae234c934fe7777aa4617d332b67bdb846c4	not-for-merge	branch 'gg/flash-attn' of https://github.com/ggml-org/llama.cpp
a647257b471067c410bb6a690487b02ae7e79dfa	not-for-merge	branch 'gg/flash-attn-32x8' of https://github.com/ggml-org/llama.cpp
4c190ba6767d7dee914c432af29fb0ef906d24c1	not-for-merge	branch 'gg/flash-attn-a' of https://github.com/ggml-org/llama.cpp
b957b8f5f6abc8221fb38923a638b90ebb966044	not-for-merge	branch 'gg/flash-attn-cuda' of https://github.com/ggml-org/llama.cpp
49a483e0f27da71d58948727711ea619aed56734	not-for-merge	branch 'gg/flash-attn-interleave-cc' of https://github.com/ggml-org/llama.cpp
1ad42b1f1ea4c929b041b0980f00a482b2404751	not-for-merge	branch 'gg/flash-attn-mask-f16' of https://github.com/ggml-org/llama.cpp
a9681febd65cbd3f372badc5f4a4d8bc1336d2d9	not-for-merge	branch 'gg/flash-attn-online' of https://github.com/ggml-org/llama.cpp
3a468e6f9f0c7dff9ed78b0f7a5af069da420606	not-for-merge	branch 'gg/flash-attn-rebase' of https://github.com/ggml-org/llama.cpp
2bf91c5306907793e41d227bda4c70b72d48dd33	not-for-merge	branch 'gg/flash-attn-simd' of https://github.com/ggml-org/llama.cpp
f249c997a8b3f9b129fe825bebd609a362e9ab9c	not-for-merge	branch 'gg/flash-attn-sync' of https://github.com/ggml-org/llama.cpp
6be02b5969ed04fb3ce336702ae3949076bb2bf4	not-for-merge	branch 'gg/flash-attn-wip' of https://github.com/ggml-org/llama.cpp
06c2d0d117e10345c293dd8e9907b6fc50e56887	not-for-merge	branch 'gg/flash-attn-wip2' of https://github.com/ggml-org/llama.cpp
6ccbd1777ad07c5dbc2eba9e83e7a2bfe9231c90	not-for-merge	branch 'gg/flash-attn-wip3' of https://github.com/ggml-org/llama.cpp
da23b56f259843ccbda705bea58457d872dc3074	not-for-merge	branch 'gg/flash-attn-wip4' of https://github.com/ggml-org/llama.cpp
608f4498802d80d11e5d5f6ac05f4e23f49a747b	not-for-merge	branch 'gg/float-pos' of https://github.com/ggml-org/llama.cpp
d7c042d1aed8a916723d711fde94a731f64c9832	not-for-merge	branch 'gg/ggml-atomic-int' of https://github.com/ggml-org/llama.cpp
cd026b48ef2cb5e5f12d2cd506ccac090cf0b729	not-for-merge	branch 'gg/ggml-cont' of https://github.com/ggml-org/llama.cpp
28f7a4d0285ac90767ac8a62bb243087df807df1	not-for-merge	branch 'gg/ggml-fix-zero-blocks' of https://github.com/ggml-org/llama.cpp
f9968f661dec1741d83b8a9f4a0da108496558ab	not-for-merge	branch 'gg/ggml-rework-cgraph' of https://github.com/ggml-org/llama.cpp
ab1b75166fab0e446b64a9802369196bb695ef78	not-for-merge	branch 'gg/ggml_scale' of https://github.com/ggml-org/llama.cpp
38061254b9fa8b6a0b6c86eef906c9d0ce2d18cd	not-for-merge	branch 'gg/gguf-fix-null-defer' of https://github.com/ggml-org/llama.cpp
fb18934a97425c42c8b32a1baaa94f0080eb051d	not-for-merge	branch 'gg/gguf-py-0.11.0' of https://github.com/ggml-org/llama.cpp
f64e4f04e7608f9fefe7c48a9abf01a8713e9e51	not-for-merge	branch 'gg/gpu-prec-tests' of https://github.com/ggml-org/llama.cpp
17b3a3e8ccd503b635f4d2a30110989c315afe02	not-for-merge	branch 'gg/grammar-refactor' of https://github.com/ggml-org/llama.cpp
e856bfed3bbd18232c121b7f6a65ec3355cf2fd3	not-for-merge	branch 'gg/hf' of https://github.com/ggml-org/llama.cpp
8c3d5b5a79765e8efb6b8427d025aff1e2697884	not-for-merge	branch 'gg/hf-args' of https://github.com/ggml-org/llama.cpp
120a1a55154332921c2cab509b282689f940bb93	not-for-merge	branch 'gg/hf-auto-dl' of https://github.com/ggml-org/llama.cpp
62d7b6c87fe0056fe64115dedded8b78fddf14e3	not-for-merge	branch 'gg/hf-test' of https://github.com/ggml-org/llama.cpp
731e7528be3872a1642a711a635e211e9ff16fa7	not-for-merge	branch 'gg/http-threads' of https://github.com/ggml-org/llama.cpp
2917e6b528a06e60c4724ffc5604de5330b55ffa	not-for-merge	branch 'gg/imatrix-gpu-4931' of https://github.com/ggml-org/llama.cpp
8b495540faa2e09758672cc9c001229ca31d1c7a	not-for-merge	branch 'gg/imatrix-remove-assert' of https://github.com/ggml-org/llama.cpp
f55b6473000dd431a916670ed8f02bf21f942310	not-for-merge	branch 'gg/indent' of https://github.com/ggml-org/llama.cpp
49bafe09863a29ab832d11ca8ea15fac475e7f9f	not-for-merge	branch 'gg/iq2-refactor-and-tests' of https://github.com/ggml-org/llama.cpp
14d757066b528495eb1c50ee33d20d743ba7a693	not-for-merge	branch 'gg/kv-compress' of https://github.com/ggml-org/llama.cpp
a041ced0fd3eee101cc592a2b9960a941b936c80	not-for-merge	branch 'gg/kv-determinism' of https://github.com/ggml-org/llama.cpp
0fc560fe96584b205ae55e9a5c22d7cc7d0555fe	not-for-merge	branch 'gg/lfs' of https://github.com/ggml-org/llama.cpp
3b6a0a817a3a5a1ff0cb5e1abeee38af90472595	not-for-merge	branch 'gg/llama-add-log' of https://github.com/ggml-org/llama.cpp
40fa68cb46fd0610420921dcf22562a88bf818bb	not-for-merge	branch 'gg/llama-disambiguate' of https://github.com/ggml-org/llama.cpp
624f7bd03bdea9e8d5c6d2ca02d87268394cc20c	not-for-merge	branch 'gg/llama-kv-cache' of https://github.com/ggml-org/llama.cpp
f648ca2cee0218bd882ffdb06791bd96818c61d4	not-for-merge	branch 'gg/llama-refactor-sampling' of https://github.com/ggml-org/llama.cpp
fe28a7b9d8d0c90d70778d0a2df92094aec2faa6	not-for-merge	branch 'gg/llama-reorganize' of https://github.com/ggml-org/llama.cpp
a97b3621cf40f264f2f73b41d87ec70ee8b79c17	not-for-merge	branch 'gg/llama-shadow-on' of https://github.com/ggml-org/llama.cpp
3750706962f73ba170817b153833d91a746ec004	not-for-merge	branch 'gg/llama3-support' of https://github.com/ggml-org/llama.cpp
f7b0233ecac4a3100c20d377fcb1582abaa4bda9	not-for-merge	branch 'gg/logits-slowdown' of https://github.com/ggml-org/llama.cpp
412735ec708875bb11c63f9f7d61ff3d77dfc966	not-for-merge	branch 'gg/metal-batched' of https://github.com/ggml-org/llama.cpp
072c56fcdbd0726b2fbaf51cf69772d204aa2428	not-for-merge	branch 'gg/metal-dequant-align' of https://github.com/ggml-org/llama.cpp
1c6cde92bb0a0bb8dae1863f720db887fd80881e	not-for-merge	branch 'gg/metal-disable-fa-256' of https://github.com/ggml-org/llama.cpp
abf0afd0d6a52627b05c2c5af2cb5120c5f047a6	not-for-merge	branch 'gg/metal-embed' of https://github.com/ggml-org/llama.cpp
a2385da59c91644cf0c2dd235898bcbf407d72e1	not-for-merge	branch 'gg/metal-fa-f16' of https://github.com/ggml-org/llama.cpp
94accca4c239ea6cd7c8848c46b67ecaa04ca0cd	not-for-merge	branch 'gg/metal-fa-f16-save' of https://github.com/ggml-org/llama.cpp
fecb81e302d7b2260a76d559376aa0f024c66571	not-for-merge	branch 'gg/metal-fattn-reqs' of https://github.com/ggml-org/llama.cpp
bd1198a67a1c74e22a7d4ff384fcc8c49c14e220	not-for-merge	branch 'gg/metal-fix-build' of https://github.com/ggml-org/llama.cpp
aa931d0375798700ea2dd441f810d1987350bb8b	not-for-merge	branch 'gg/metal-fix-fa' of https://github.com/ggml-org/llama.cpp
a95225cdfd7286f965311790f4e3fa61141b0d78	not-for-merge	branch 'gg/metal-fix-fa-2' of https://github.com/ggml-org/llama.cpp
eaf34ba0cdcd7690f4b281b309c9bbc2f3e7b3e8	not-for-merge	branch 'gg/metal-mmid-max-rows' of https://github.com/ggml-org/llama.cpp
4ff0831ce641f895be53181e4004f9239e1ddd97	not-for-merge	branch 'gg/metal-mul-mat-f16' of https://github.com/ggml-org/llama.cpp
3d1fe1bb4d0123fdd2469c089f4d7ed6bc138b79	not-for-merge	branch 'gg/metal-mul-mat-write-opt' of https://github.com/ggml-org/llama.cpp
bf3494345ec6043612678b133a41bb28642c087d	not-for-merge	branch 'gg/metal-mul-mv-new' of https://github.com/ggml-org/llama.cpp
dafedd33d2e64530e691d9f687fdff0f18fd4b6a	not-for-merge	branch 'gg/metal-mul-mv-new-save2' of https://github.com/ggml-org/llama.cpp
3c8a2a83feb01390a67762eb37655815a86f3617	not-for-merge	branch 'gg/metal-mul-mv-new-save3' of https://github.com/ggml-org/llama.cpp
9f51f3e69541c026fb8c0a68ead37446103a7b62	not-for-merge	branch 'gg/metal-opt-mul-mat-id' of https://github.com/ggml-org/llama.cpp
8c1b186cb5eac4abd26b73a8cb2a2248808491e7	not-for-merge	branch 'gg/metal-q4_0-opt' of https://github.com/ggml-org/llama.cpp
d4a1923d4e8000f86d72a2bc1d3a0053323cb285	not-for-merge	branch 'gg/nix-remove-opencl' of https://github.com/ggml-org/llama.cpp
98f948b9d072e293faceb795b69ce3e5805ecf65	not-for-merge	branch 'gg/no-char32_t' of https://github.com/ggml-org/llama.cpp
3cb1c348b3481f39d244b6b0cd5afb04aa6bd460	not-for-merge	branch 'gg/pad-kv-cache' of https://github.com/ggml-org/llama.cpp
fc5f334689e25be2efdd6c43a734bcc6337be53e	not-for-merge	branch 'gg/per-layer-kv' of https://github.com/ggml-org/llama.cpp
d2f1e0daccaeacfd04edd1721fa05329a8a5d3ab	not-for-merge	branch 'gg/phi-2' of https://github.com/ggml-org/llama.cpp
a462159c4360ef66c9d949dce501744bc36eda87	not-for-merge	branch 'gg/phi-2-2' of https://github.com/ggml-org/llama.cpp
3c734f4941f116fb1a1d8cf50ed1f26c315e7480	not-for-merge	branch 'gg/plamo-test' of https://github.com/ggml-org/llama.cpp
56c047156a438daa6698af7e92814e9967131c84	not-for-merge	branch 'gg/py-minor-fixes' of https://github.com/ggml-org/llama.cpp
f6ea7a093c6b7eb348071d158290902ceb7459e8	not-for-merge	branch 'gg/quantize-fallback' of https://github.com/ggml-org/llama.cpp
af99c6fbfc815df7dad94d8c1f20d55927b2203a	not-for-merge	branch 'gg/quantum-k-cache' of https://github.com/ggml-org/llama.cpp
03e940cdec1b91b848b9652e61cc3a2f4541d171	not-for-merge	branch 'gg/refactor-alibi-2' of https://github.com/ggml-org/llama.cpp
7cfde7819083eaa63a423b7a82a0d4b9c189b0b9	not-for-merge	branch 'gg/remove-gqa-check-4657' of https://github.com/ggml-org/llama.cpp
956bb14595c1c6864bd890b961cd68ea83bbb434	not-for-merge	branch 'gg/remove-instruct' of https://github.com/ggml-org/llama.cpp
ccb45186d092118c8cd4d01e7dff0cd2bcb45cce	not-for-merge	branch 'gg/remove-k-quants-per-iter' of https://github.com/ggml-org/llama.cpp
47c662b0de47a9e4a2e310c933f81c767e79f684	not-for-merge	branch 'gg/rename-n_ctx' of https://github.com/ggml-org/llama.cpp
0a9bc301acace74fe36944017c647a338c04affa	not-for-merge	branch 'gg/repeng' of https://github.com/ggml-org/llama.cpp
bddcc5f985fcc124c54acaf582cfaa01d8811c34	not-for-merge	branch 'gg/replace-all' of https://github.com/ggml-org/llama.cpp
a0242a833cf6137e5ae033ba34bcc7fc6339c251	not-for-merge	branch 'gg/rmse_quantization' of https://github.com/ggml-org/llama.cpp
34bdbed481cc2f50ba4c411bb93fd39b68a3765b	not-for-merge	branch 'gg/rpc-fix-misaligned' of https://github.com/ggml-org/llama.cpp
a6648b9df77c531ad1e493b8781fd41762e88f0b	not-for-merge	branch 'gg/server-chunked-prefill' of https://github.com/ggml-org/llama.cpp
4bb03cade0db5b9010c3c5537cb4aaeed674afd8	not-for-merge	branch 'gg/server-debug-win' of https://github.com/ggml-org/llama.cpp
b8d1b1a5e18875207212005778c1343e42ed4606	not-for-merge	branch 'gg/server-fix-infill' of https://github.com/ggml-org/llama.cpp
9e4d62e6abb9096fa93f6d7756547ec495888eb8	not-for-merge	branch 'gg/server-fix-prompt' of https://github.com/ggml-org/llama.cpp
33d7b70c881b1f9ebabd381daf3ad9cb283ce028	not-for-merge	branch 'gg/server-fix-spec' of https://github.com/ggml-org/llama.cpp
81611bef729321117e603e6603dd8355b4908099	not-for-merge	branch 'gg/server-fix-spec-ctx-shift' of https://github.com/ggml-org/llama.cpp
24096933b0fbc89b0af6b3b187c02dfa8647271a	not-for-merge	branch 'gg/server-infill-empty-prompt-4027' of https://github.com/ggml-org/llama.cpp
d86e23101ee02a39a8c0952818efce02c2524f8c	not-for-merge	branch 'gg/server-logs' of https://github.com/ggml-org/llama.cpp
956af1552adf8e96c5bbf7e05d5cd628e523b07b	not-for-merge	branch 'gg/server-update-js' of https://github.com/ggml-org/llama.cpp
0085f94936ecf29f778989355558780d66e42541	not-for-merge	branch 'gg/server-v1-completion' of https://github.com/ggml-org/llama.cpp
eb594c0f7d9528b942e50fae508dbcada597ac06	not-for-merge	branch 'gg/soft-max-ext' of https://github.com/ggml-org/llama.cpp
5e6dad9322b47bc072ae7f85513a07f23118a868	not-for-merge	branch 'gg/speculative-experiments' of https://github.com/ggml-org/llama.cpp
33bdee667e964fe4f6bc5237304bfcd6d3258135	not-for-merge	branch 'gg/speculative-fix-oob' of https://github.com/ggml-org/llama.cpp
b83cae088c2e1d069a83560a290b13a836828cd7	not-for-merge	branch 'gg/speculative-infill' of https://github.com/ggml-org/llama.cpp
0f2bf555027720d16423a70a53d7fed45a4fdcbd	not-for-merge	branch 'gg/speculative-update' of https://github.com/ggml-org/llama.cpp
865066621b195ffcaae71f379ff45c627b000d03	not-for-merge	branch 'gg/swiftui-bench' of https://github.com/ggml-org/llama.cpp
593458090540363ad5d22558a8fa7675668e919d	not-for-merge	branch 'gg/system-info-llamafile' of https://github.com/ggml-org/llama.cpp
f32f30bc57b7b297c6900a179947f7f25a59f2d1	not-for-merge	branch 'gg/test-arm' of https://github.com/ggml-org/llama.cpp
a085a8323aef383674759b777d3d5e02e56306a4	not-for-merge	branch 'gg/test-bench' of https://github.com/ggml-org/llama.cpp
6b2f496409330259da5fe9361ece56010a4664a7	not-for-merge	branch 'gg/test-embd' of https://github.com/ggml-org/llama.cpp
114ab6347e0e21e49d55d45a6557c0eb1f2309f3	not-for-merge	branch 'gg/tfs-ob1' of https://github.com/ggml-org/llama.cpp
5ddad95e5c8a7483c2c2411de76314e1dd7ad50c	not-for-merge	branch 'gg/tmp-ci' of https://github.com/ggml-org/llama.cpp
6e873e561a05bc3df7455233366ecc0b5c550267	not-for-merge	branch 'gg/tokenizer-cleanup' of https://github.com/ggml-org/llama.cpp
76be02aebc063ffb8341b98250386211a1f1c37b	not-for-merge	branch 'gg/try-fix-sycl-iq1_s' of https://github.com/ggml-org/llama.cpp
bc82fc2ed8db37e0819c07ca38c440b25b4972ad	not-for-merge	branch 'gg/ttfb' of https://github.com/ggml-org/llama.cpp
8412561c4b39a540e53e7fdde0078e5ab3adb908	not-for-merge	branch 'gg/unary-non-cont' of https://github.com/ggml-org/llama.cpp
3e92f4ecbe332fde1f40d4d47dff107a6544e15b	not-for-merge	branch 'gg/unicode-refactor' of https://github.com/ggml-org/llama.cpp
1fb563ebdcceca145a02c35e6ad0b4859609dddd	not-for-merge	branch 'gg/update-phi2-convert' of https://github.com/ggml-org/llama.cpp
0cf9a067994fbce9ef31827f7a98e66552410f3b	not-for-merge	branch 'gg/vocab-fix-no-vocab' of https://github.com/ggml-org/llama.cpp
d273bfd2c98148fab309f978c44ec2e8c24d1c4d	not-for-merge	branch 'ggml-backends' of https://github.com/ggml-org/llama.cpp
d45c1631bc81bceef6106d319fb177ecad32daa0	not-for-merge	branch 'ggml-backends-metal' of https://github.com/ggml-org/llama.cpp
4b3cb98d46770e6166e22ebe1accce421e75d3df	not-for-merge	branch 'ggml-impl' of https://github.com/ggml-org/llama.cpp
8a86b95e8776899367ac7b6162f7f9ec5aed8c06	not-for-merge	branch 'ggml-quants' of https://github.com/ggml-org/llama.cpp
66a66a05a8c509e57e170659182f96165d2e8112	not-for-merge	branch 'gguf' of https://github.com/ggml-org/llama.cpp
33a5517d8786be474292236c1f9f29dc59bf2e2e	not-for-merge	branch 'gguf-64bit' of https://github.com/ggml-org/llama.cpp
ba44776dc2c7fcc00da6bf8df96140cfd7cf868c	not-for-merge	branch 'gguf-fix-publish' of https://github.com/ggml-org/llama.cpp
0248ca811e076ac0017e4cb35651ca6b57c3bfd5	not-for-merge	branch 'gguf-pip' of https://github.com/ggml-org/llama.cpp
488e03200e138b6f207d379740ed4e585a8085cd	not-for-merge	branch 'gguf-publish-ci' of https://github.com/ggml-org/llama.cpp
af1c9966c8ef1d160bc83bb8df898f5897a19d34	not-for-merge	branch 'gguf-python' of https://github.com/ggml-org/llama.cpp
6a9e6375b5b586eeeb3c7b4959c1ef79dd73ffac	not-for-merge	branch 'gguf-write-single-pass' of https://github.com/ggml-org/llama.cpp
511055722e925fcd2561cfe45627a82582b53008	not-for-merge	branch 'gguf-write-tensor' of https://github.com/ggml-org/llama.cpp
a362c74aa2f5e1fae5b211cadbc41bdde9669041	not-for-merge	branch 'graph-profiler' of https://github.com/ggml-org/llama.cpp
b54afce9f42652e59c81e978e7cd5f9861a7d4e9	not-for-merge	branch 'gritlm-pr' of https://github.com/ggml-org/llama.cpp
eedd42e3767efb49cd497cdef3943397b42ee935	not-for-merge	branch 'hp/tmp/kv-cache-defrag' of https://github.com/ggml-org/llama.cpp
9fd1e83f6df113118b146a10840e42953773db22	not-for-merge	branch 'ik/better_q2_k_s' of https://github.com/ggml-org/llama.cpp
5440a127c7df74cae45cda93282fc307a6655363	not-for-merge	branch 'ik/even_better_iq1s' of https://github.com/ggml-org/llama.cpp
ccc78a200e5568a861fba95e7fdbac11cd737a05	not-for-merge	branch 'ik/faster_hellaswag' of https://github.com/ggml-org/llama.cpp
d34472c1241fdfd960ad40d31009eb27c9a403d7	not-for-merge	branch 'ik/fix_hellaswag' of https://github.com/ggml-org/llama.cpp
719a08713848441334035794d70736f7671949ff	not-for-merge	branch 'ik/fix_iq3xxs_metal' of https://github.com/ggml-org/llama.cpp
68e4fed4d93d886ae4b4d5d6d9cc6c8602f83a7d	not-for-merge	branch 'ik/fix_k_cache_backend_tests' of https://github.com/ggml-org/llama.cpp
4246b71ad736ebe472ae72c492a7b5ee8377db56	not-for-merge	branch 'ik/fix_warnings' of https://github.com/ggml-org/llama.cpp
91c453fb111fea0c1ce1c4c09a52b4631f0e31fd	not-for-merge	branch 'ik/ggml-quants-cpp' of https://github.com/ggml-org/llama.cpp
f0cbb6ddf6b314693cdc536994152bb85731f281	not-for-merge	branch 'ik/i-quants-64' of https://github.com/ggml-org/llama.cpp
bb9abb5cd8d8b2517a573efc291528f47c6f6ee9	not-for-merge	branch 'ik/imatrix_legacy_quants' of https://github.com/ggml-org/llama.cpp
5c977221d218053a01ca61841d3b3e7d550d28d2	not-for-merge	branch 'ik/iq1_s' of https://github.com/ggml-org/llama.cpp
9bfcb16fd3225b270b4c78fea87e63fb0daf2e96	not-for-merge	branch 'ik/iq2_2.31bpw' of https://github.com/ggml-org/llama.cpp
d4dfc250cc64c37d57b12b6d88b7b81c707d3047	not-for-merge	branch 'ik/iq3_s_faster' of https://github.com/ggml-org/llama.cpp
31cecc8734537b38052a61c7060fabcf6094e35b	not-for-merge	branch 'ik/iq3_s_multiplier' of https://github.com/ggml-org/llama.cpp
0e826d12a51ee5d7d68800715ca9baacb6ee14bb	not-for-merge	branch 'ik/quantize_not_repeating' of https://github.com/ggml-org/llama.cpp
9c5fd6be14b8618b4846c50a1e7f23181899d171	not-for-merge	branch 'ik/quantize_with_kv_overrides' of https://github.com/ggml-org/llama.cpp
6f20e2672f37be64509f355caafc928a97adad86	not-for-merge	branch 'ik/test_quantize_fns' of https://github.com/ggml-org/llama.cpp
9f805264dc2b22c05289f0bf220e79dcbb10a5d9	not-for-merge	branch 'ik/try_fix_iq1s_sycl' of https://github.com/ggml-org/llama.cpp
a710d58d8867c0b494023b799bfd41573f6a439d	not-for-merge	branch 'ik/try_fix_rocm_k_cache' of https://github.com/ggml-org/llama.cpp
4baa85633a276d3bb95fa89271b28a3551829829	not-for-merge	branch 'jed/spm-clblast' of https://github.com/ggml-org/llama.cpp
a8046c888ac55e22bcbbdae5d59ec08ae5ac5368	not-for-merge	branch 'jg/gguf-refactor' of https://github.com/ggml-org/llama.cpp
ba421dd04ea4a878d0085ad093222f996afc1a27	not-for-merge	branch 'jg/llama-sanitize' of https://github.com/ggml-org/llama.cpp
f8e9f1142893240102e32de06c7b55ea02ad4e2a	not-for-merge	branch 'kv-cache-opts' of https://github.com/ggml-org/llama.cpp
d0445a2effc1ddd3281e80aa66479d145930f4eb	not-for-merge	branch 'llama-metadata' of https://github.com/ggml-org/llama.cpp
afb3929279c71f74a28c100f991658c082319715	not-for-merge	branch 'llama-refactor' of https://github.com/ggml-org/llama.cpp
7923b70cb8033ccf4097b7a95013fa6b0ad22ecd	not-for-merge	branch 'llama-refactor-norm' of https://github.com/ggml-org/llama.cpp
344e9aeac5d87ed2977d7bdb3af0f93c5b76c0ea	not-for-merge	branch 'llama-run-utf-8' of https://github.com/ggml-org/llama.cpp
26cc1bd7a2adc564a03ebb8b321468b3ab744f60	not-for-merge	branch 'llama_server_completions' of https://github.com/ggml-org/llama.cpp
ff6e39f1389408863affd30d15860869573c49e5	not-for-merge	branch 'llama_server_timings' of https://github.com/ggml-org/llama.cpp
932589c0efe73480b22eca6a1e2a01c230ef5258	not-for-merge	branch 'llava-fix-offloading' of https://github.com/ggml-org/llama.cpp
a8796f96090fa037855bf2829786464008d32f25	not-for-merge	branch 'llm-build-context' of https://github.com/ggml-org/llama.cpp
7420bef83e4f5077e7ef140174c1abf72668abb9	not-for-merge	branch 'llm-reuse-constants' of https://github.com/ggml-org/llama.cpp
8d8b76d469763fca498d55e04c8b10a18a545c3b	not-for-merge	branch 'lookahead' of https://github.com/ggml-org/llama.cpp
bc28aaa8c20b81d6d2da56f954854a87ac6d2219	not-for-merge	branch 'lto' of https://github.com/ggml-org/llama.cpp
f3a84b2e0d03aca09fc6fd2cd873c9fd162a0f4e	not-for-merge	branch 'metal-cont-bug' of https://github.com/ggml-org/llama.cpp
2f689dee06592eedab53fcb822463eac1b238b87	not-for-merge	branch 'metal-fix-norm' of https://github.com/ggml-org/llama.cpp
6b9554a740d79b22c42c2058bfc05f27fd9199c7	not-for-merge	branch 'metal-improve-batching' of https://github.com/ggml-org/llama.cpp
46868a499e2601f46d886c2aaa9cbe9d4b416d98	not-for-merge	branch 'metal-soft-max' of https://github.com/ggml-org/llama.cpp
e1241d9b461816b679eaf6951631287687a18f66	not-for-merge	branch 'mixtral' of https://github.com/ggml-org/llama.cpp
33a004e9cc04288b0e798dcc0b0d373a7a0fc758	not-for-merge	branch 'mlx-challenge' of https://github.com/ggml-org/llama.cpp
c9c820ff36b0d80b85fe17447d512201d3f23185	not-for-merge	branch 'mmap' of https://github.com/ggml-org/llama.cpp
15067374999644dbfe993dd42644556a30f0c1cc	not-for-merge	branch 'mmap-pages-stats' of https://github.com/ggml-org/llama.cpp
e7e7b114556172d8dae0bbd9f13887a63949a8f5	not-for-merge	branch 'mul-mat-pad' of https://github.com/ggml-org/llama.cpp
8c2b881281ba814ea15ed8455e51107f3c2e7791	not-for-merge	branch 'norm-quants' of https://github.com/ggml-org/llama.cpp
b4e70822f6282a6b3c9ae53a282d30c9d5ccf70f	not-for-merge	branch 'norm-quants-rebase' of https://github.com/ggml-org/llama.cpp
2991954b7dcbc7a5a66e11e7eb59a10ac2b1636d	not-for-merge	branch 'optimize_fmt' of https://github.com/ggml-org/llama.cpp
d57cb9c2941531f090b71d2cde5ec7ad2098f237	not-for-merge	branch 'passkey' of https://github.com/ggml-org/llama.cpp
12aa74ba7df77d50e54d3a6f5c75b8f6ba3e92b2	not-for-merge	branch 'patch-1' of https://github.com/ggml-org/llama.cpp
cb79f8a2d8c0c36f59e1d5445411acb01645f2f1	not-for-merge	branch 'perf-study' of https://github.com/ggml-org/llama.cpp
947158ee528fe856697fcf082cb26190269756c9	not-for-merge	branch 'podman' of https://github.com/ggml-org/llama.cpp
f86b9d152cc81baa57f1fbee14271d2fe88bac0e	not-for-merge	branch 'pr/4484' of https://github.com/ggml-org/llama.cpp
2d3fc54ac6707f77be7779e576836d684635b3cf	not-for-merge	branch 'pr_add_intel_amx_support' of https://github.com/ggml-org/llama.cpp
6e299132e7f143ec6abb8f26ee14b0040592c983	not-for-merge	branch 'prepare-PR-of-minicpm-v2.5-gg' of https://github.com/ggml-org/llama.cpp
71e6ae3779708f828d4b9077875583f15a400eb9	not-for-merge	branch 'q4_0-q4_2-range-fix' of https://github.com/ggml-org/llama.cpp
4aeee216fdfbbe1a0b8433ba487b6a57e437aa37	not-for-merge	branch 'q4_1_more_accel' of https://github.com/ggml-org/llama.cpp
66ea164e1d6a0b95628123ce39f66ab76b8a69f0	not-for-merge	branch 'q4_1_more_accel_kahan' of https://github.com/ggml-org/llama.cpp
711224708d0977a4cf7138eacaf5a70a6ac5474d	not-for-merge	branch 'q4_1_more_accel_loopsplit' of https://github.com/ggml-org/llama.cpp
102cd98074f62aab00b1e591bab8ac48f01113b7	not-for-merge	branch 'q4_3-range-fix' of https://github.com/ggml-org/llama.cpp
4b8d5e389085a1d986877dbc86976361f2778846	not-for-merge	branch 'quant-attn' of https://github.com/ggml-org/llama.cpp
049236313758a38671e2715813a2ce6c3d8ec2da	not-for-merge	branch 'refactor-mpi' of https://github.com/ggml-org/llama.cpp
e116eb638c9a426d679a9f756d27f13eb6ce626a	not-for-merge	branch 'remove-vzip' of https://github.com/ggml-org/llama.cpp
5261aee8d86e71b116cc8f1031687e27a50c2b5f	not-for-merge	branch 'rev-sampling' of https://github.com/ggml-org/llama.cpp
f30aca84b28ff3ef0043380a509371eb241176f7	not-for-merge	branch 'revert-11820-vers_fix' of https://github.com/ggml-org/llama.cpp
b5b02703722528fb2c8c20ce6db7d5c577233097	not-for-merge	branch 'revert-5901-fix_set_gpu' of https://github.com/ggml-org/llama.cpp
46325233c9167c48ae36e17aed732fb57e01edda	not-for-merge	branch 'revert-7777-host-usm-context-fix' of https://github.com/ggml-org/llama.cpp
3ef358fffd747133d1069d5e53314c585d358547	not-for-merge	branch 'revert-pool' of https://github.com/ggml-org/llama.cpp
bbfc62ac2f11c4c92f8c9de9af2b851880f8aa81	not-for-merge	branch 'sampling-greedy-with-probs' of https://github.com/ggml-org/llama.cpp
56ba00b9230aa1c6ef95282d90917bb2277fa0a8	not-for-merge	branch 'sampling-refactor' of https://github.com/ggml-org/llama.cpp
15267192c070ec86de52fe13f841625df7027f82	not-for-merge	branch 'scratch' of https://github.com/ggml-org/llama.cpp
28046d1e52017cfc0a61a7088762918ea64decb0	not-for-merge	branch 'server-cfg' of https://github.com/ggml-org/llama.cpp
21b70babf759f30b52cef6cb4ef1a206e56ca70e	not-for-merge	branch 'server-oai-compat' of https://github.com/ggml-org/llama.cpp
5ab6c2132aad2354092a26c096cc5c8f55801141	not-for-merge	branch 'server-parallel' of https://github.com/ggml-org/llama.cpp
c0f4d54870568c2977db9327223c5c2546bda018	not-for-merge	branch 'server-rev' of https://github.com/ggml-org/llama.cpp
9605c5fb281568c0ed0e3f1060bf47f4c4e5efec	not-for-merge	branch 'shards-lang/gio/visionos-ci' of https://github.com/ggml-org/llama.cpp
20e12112fda76906d006f5af42b8099163c515cc	not-for-merge	branch 'sl/aligned-alloc-no-abort' of https://github.com/ggml-org/llama.cpp
5de9b743f83da5cfc70fcc6698cce9b26270d596	not-for-merge	branch 'sl/async-weight-copy' of https://github.com/ggml-org/llama.cpp
afc4a7de65f416e9fe1cb1248b4d7e4c104100df	not-for-merge	branch 'sl/auto-flash-attn' of https://github.com/ggml-org/llama.cpp
210e4691149d694ecdd8f5e7eb8a96855ef98a28	not-for-merge	branch 'sl/cuda-f16-fix3' of https://github.com/ggml-org/llama.cpp
1ca802a3e0314b977b4e53ad0dd729fc2f9f487c	not-for-merge	branch 'sl/cuda-fattn-par-test' of https://github.com/ggml-org/llama.cpp
518b75260b1e4ef9f3eb308b5302bd8bfaad4893	not-for-merge	branch 'sl/cuda-uma' of https://github.com/ggml-org/llama.cpp
2e54433a9ddc7eb36d05c297b4f24744e778a34f	not-for-merge	branch 'sl/custom-tensor-offload' of https://github.com/ggml-org/llama.cpp
d857e5192ec34b6b6b4c98e24baa738309faf97b	not-for-merge	branch 'sl/detect-imatrix-nan' of https://github.com/ggml-org/llama.cpp
e9095e6098dc21ec51f97f96dd7d9d3e18ed9753	not-for-merge	branch 'sl/dio-test' of https://github.com/ggml-org/llama.cpp
94061d58e747f24e574d4de8cf8c0dcd1b89cc3e	not-for-merge	branch 'sl/disable-pp-nkvo' of https://github.com/ggml-org/llama.cpp
cad8abb49b52b41c0ab3e8d4acd019fc0de655a8	not-for-merge	branch 'sl/dump-allocs' of https://github.com/ggml-org/llama.cpp
f7d4b7c3439cfc24745f5ada583aa3b4441d7ff5	not-for-merge	branch 'sl/fix-docker-main-server-build' of https://github.com/ggml-org/llama.cpp
3d2e79da7ff48bef6887494b395c94e7c0cd020f	not-for-merge	branch 'sl/fix-docker-omp' of https://github.com/ggml-org/llama.cpp
6b0248c29a224c767ae29551cfd6b40ae10ffa19	not-for-merge	branch 'sl/fix-omp-one-thread' of https://github.com/ggml-org/llama.cpp
dcab343f2f06223218635b5975829610d2422541	not-for-merge	branch 'sl/fix-ppl-seq-max' of https://github.com/ggml-org/llama.cpp
5271c7566659081a626013989375cd52e4ad4762	not-for-merge	branch 'sl/fix-quant-kv-shift' of https://github.com/ggml-org/llama.cpp
c3e2bb6dcf41b0a7ffca19469eab4ece50595372	not-for-merge	branch 'sl/fix-rpc-nkvo' of https://github.com/ggml-org/llama.cpp
630bce5a7fa4b1810ed2b1ab4435a194332e23c3	not-for-merge	branch 'sl/fix-sched-reserve' of https://github.com/ggml-org/llama.cpp
4fc8673d09e6a213cfaf3b098e8582c20780a886	not-for-merge	branch 'sl/llama-bench-headers' of https://github.com/ggml-org/llama.cpp
cfb0ae7e4c14478099a8fe83beed87db6e19608e	not-for-merge	branch 'sl/more-imatrix-nan-fixes' of https://github.com/ggml-org/llama.cpp
de9d2c6f096a248cac8ab4bb5fae9a25fbc00067	not-for-merge	branch 'sl/pr-releases' of https://github.com/ggml-org/llama.cpp
9127800d83ce88f966918655e93f8f4c5ab82ef1	not-for-merge	branch 'sl/prepare-next-graph' of https://github.com/ggml-org/llama.cpp
5f8720fb7b019f8591fa805265052fef433dbd52	not-for-merge	branch 'sl/rpc-backend-cpy' of https://github.com/ggml-org/llama.cpp
7b60ab918a884493e67037d648e69a394d92a783	not-for-merge	branch 'sl/tbops-params-filter' of https://github.com/ggml-org/llama.cpp
f3974cabac841b9b35283a731bc31203288633d4	not-for-merge	branch 'sl/test-mul-mat-backend' of https://github.com/ggml-org/llama.cpp
1e6e363d7f902a1c05bbfbf133c32293a2e9a11c	not-for-merge	branch 'sl/zero-max-size' of https://github.com/ggml-org/llama.cpp
847896aba762bdba22e17b44e602e5adeb84547f	not-for-merge	branch 'speculative' of https://github.com/ggml-org/llama.cpp
c79d130f74cdfb18cb47fe7ed7a0b56e2774c6f1	not-for-merge	branch 'speculative-grammar' of https://github.com/ggml-org/llama.cpp
ad2727d09143ea3931d4ad271baa7a1831a96d82	not-for-merge	branch 'speculative-tree' of https://github.com/ggml-org/llama.cpp
95dc4d7270e04bef3792a61be9bb045cb74a9fc4	not-for-merge	branch 'steering' of https://github.com/ggml-org/llama.cpp
92a4f8687933c9f0a6847097e1a5086f6cd44720	not-for-merge	branch 'support-starcoder-fix' of https://github.com/ggml-org/llama.cpp
8233009d4d3847a44824d85714371abfa2e2372d	not-for-merge	branch 'support_device_reg' of https://github.com/ggml-org/llama.cpp
73ef3f769c07eb2fd9800bfce7f30bc7ec597706	not-for-merge	branch 'sycl-cmake-append' of https://github.com/ggml-org/llama.cpp
9aeb0e1f751048c7a0863321e3cfd4cd63e46b40	not-for-merge	branch 'sycl-conv-op' of https://github.com/ggml-org/llama.cpp
d32a8f61421f2f27e0c1f5b12215ecb47e1fbddd	not-for-merge	branch 'sycl-global-variables' of https://github.com/ggml-org/llama.cpp
ff0aa3abd1c2ca7aa7b8a020c6f59f90d259ce65	not-for-merge	branch 'sycl-mul-mat-id' of https://github.com/ggml-org/llama.cpp
6494509801647e270aad076a9b50f17e863e0a60	not-for-merge	branch 'sycl-onednn-convolution' of https://github.com/ggml-org/llama.cpp
989e15b3c19b59a2bbd2842854cf90ef94087f03	not-for-merge	branch 'sycl_q3s_q1s' of https://github.com/ggml-org/llama.cpp
8ffa8bec389e4e9792b0a84f2acae46c7a9471fd	not-for-merge	branch 'sync-ggml-25-02-28' of https://github.com/ggml-org/llama.cpp
3a0dcb39207a18ab3f8d825914d0c4359ae9736d	not-for-merge	branch 'tcp_server' of https://github.com/ggml-org/llama.cpp
124e4dced2c5cacc944364cb7b540056255911b1	not-for-merge	branch 'test-bench' of https://github.com/ggml-org/llama.cpp
f46db27ea0691f72287bb6b9fb165a8b3dc18b71	not-for-merge	branch 'test-mac-os-ci' of https://github.com/ggml-org/llama.cpp
29fe516913f1b9d7ffa5bebe6ebdd466848fa6b9	not-for-merge	branch 'test-mmv' of https://github.com/ggml-org/llama.cpp
5cc672a9a537ab194ccc4874b20bdc8267bf6eb0	not-for-merge	branch 'try-fix-metal' of https://github.com/ggml-org/llama.cpp
b9bb4cbe864f7ba683ee2dec7ee6f89a72918aa7	not-for-merge	branch 'upd-issue-templates' of https://github.com/ggml-org/llama.cpp
7764ab911d2e3c68974e8159d079553357b0ad26	not-for-merge	branch 'update_sycl_doc' of https://github.com/ggml-org/llama.cpp
86548050276bfef6b18daa52b6dcb9ddc514102b	not-for-merge	branch 'xsn/ci_legacy_gg' of https://github.com/ggml-org/llama.cpp
c9e7cbb08b70b73729f5e73ec27064ccb51b271c	not-for-merge	branch 'xsn/tmp_jinja_safer' of https://github.com/ggml-org/llama.cpp
