upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • aee6d5da2c Fix more missing backend stuff (and Python errors) Piotr Wilkin 2026-03-29 01:57:02 +01:00
  • 1621ff9003 add second dimension to reported tensors, fix Mac build, add missing initializer to all backends Piotr Wilkin 2026-03-29 01:49:52 +01:00
  • 678918d675 feat: cool profiler thingy Piotr Wilkin 2026-03-29 01:14:09 +01:00
  • a8dc0e3269 server : allow text-only slot save/restore with mtmd (#25076) b10045 Chipmunk 2026-07-16 21:26:44 +09:00
  • a55a8c5266 convert : fix dflash target tokenizer mismatch during conversion (#25733) Ruixiang Wang 2026-07-16 14:19:47 +02:00
  • 79bba02a67 CUDA: Support CUDA Virtual Devices (#25228) b10043 Anav Prasad 2026-07-16 03:37:35 -07:00
  • 3f08ef2c51 Enable CUDA graphs on volta+turing (#25749) b10042 Alexander Heisler 2026-07-16 05:56:19 -04:00
  • 8ee54c8b32 server: Ignore empty / non-existing Origin headers (#25756) b10041 Sebastian Dröge 2026-07-16 12:26:51 +03:00
  • c7d8722922 ggml-cuda : restore prop.integrated on HIP builds (#24233) b10040 liminfei-amd 2026-07-16 17:10:08 +08:00
  • 5839ba3524 CUDA: dedup MoE gate/up activation quantization (#25441) Pranesh Gonegandla 2026-07-16 07:02:25 +00:00
  • a320cbfcb7 ci : add official website link to release notes (#25728) b10038 Georgi Gerganov 2026-07-16 08:30:42 +03:00
  • 56d6e9dde2 quant : allow using manual tensor types with --pure (#25716) b10037 Georgi Gerganov 2026-07-16 08:30:20 +03:00
  • 3dafb585f8 opencl: disable FA and MoE weights repack to work around compiler issues for Adreno 850 GPU (#25745) b10036 Hongqiang Wang 2026-07-15 20:53:14 -07:00
  • 602f828b4d cuda: extract Q1_0 elements via __byte_perm (#25628) b10035 David Friehs 2026-07-16 05:39:17 +02:00
  • 505b1ed15c opencl: exclude some moe kernels on Adreno a7x (#25698) b10034 Hongqiang Wang 2026-07-15 12:02:19 -07:00
  • 32beb244f5 ui: Agentic Content UX improvements (#25450) Aleksander Grygier 2026-07-15 20:31:45 +02:00
  • 3b53219361 cuda : CUDA GGML_OP_LIGHTNING_INDEXER implementation (generic vector kernel + wmma kernel) (#25545) b10032 fairydreaming 2026-07-15 19:57:52 +02:00
  • aff6eb6e75 tokenize : drop --stdin mutual-exclusion check (#25672) b10031 Adrien Gallouët 2026-07-15 18:41:51 +02:00
  • c3d47e696b opencl: fix two issues on flash attention for Adreno a7x (#25697) Hongqiang Wang 2026-07-15 09:08:40 -07:00
  • f6f12e43fa CUDA: tighter MMQ src1 buffer size for native fp4 (#25613) leonardHONG 2026-07-15 23:21:22 +08:00
  • 956973c764 Fix crash with draft-simple (#25720) Gaurav Garg 2026-07-15 19:51:34 +05:30
  • a582222290 server: fix read_file append_loc space breaking edit_file match (#25705) Pascal 2026-07-15 13:46:46 +02:00
  • a05df0a81a ui: fix thinking menu never appearing in single-model mode (#25637) Pascal 2026-07-15 13:39:21 +02:00
  • a3e5b96ac5 cuda : relax tensor contiguity requirements for quantized concat (#25678) b10025 fairydreaming 2026-07-15 13:36:32 +02:00
  • c81029373d ci : add HF_TOKEN to self-hosted workflows (#25706) Georgi Gerganov 2026-07-15 14:34:53 +03:00
  • b3c9d1b846 metal: fuse snake activation (mul, sin, sqr, mul, add) (#25459) Pascal 2026-07-15 12:53:31 +02:00
  • f955e394bf ggml: add f16 out_prod support for CPU and out_prod op for Vulkan (#23997) Michael Lamothe 2026-07-15 18:46:56 +10:00
  • 33a75f41c3 DeepseekV4: reduce graph splits (#25702) b10021 Aman Gupta 2026-07-15 15:47:18 +08:00
  • d3fba0c79d sycl : fix get_rows Q2_K, Q4_K, Q5_K (#25656) b10020 Neo Zhang 2026-07-15 15:32:28 +08:00
  • ae9291e16b sycl : support kernel type fp16 for conv2d_dw (#25653) b10019 Neo Zhang 2026-07-15 15:31:10 +08:00
  • 22b208b1ca sycl : implement xielu op (#25550) b10018 Andrew Smith 2026-07-15 00:29:12 -07:00
  • 0e148a573f sycl: Increase minimum buffer size for USM system allocations (#25525) b10017 Francois Dugast 2026-07-15 09:28:24 +02:00
  • 32b741c336 [SYCL] Flash Attention with XMX engine via oneDNN (#25222) b10016 hmscider 2026-07-15 03:26:53 -04:00
  • 12127defda opencl: do not use clCreateBufferWithProperties when targeting CL 2.x (#25673) b10015 Hongqiang Wang 2026-07-14 19:53:56 -07:00
  • 00fa7cb284 opencl: handle OOB write in noshuffle GEMV kernels (odd ne01) (#25640) Hongqiang Wang 2026-07-14 13:46:54 -07:00
  • a4ce2595c5 opencl: avoid the vec path in GEMV for unaligned row stride (#25671) Hongqiang Wang 2026-07-14 12:27:56 -07:00
  • c71854292f hexagon: fix hmx-queue signal enum-narrowing problem (#25677) b10012 Chyan 2026-07-15 03:27:09 +08:00
  • bf2c86ddc0 server : refactor prompt cache state ownership (#25649) b10011 Georgi Gerganov 2026-07-14 18:25:52 +03:00
  • 6e52db5b72 server: add --cors-* options (#25655) b10010 Xuan-Son Nguyen 2026-07-14 17:23:44 +02:00
  • 236ab574e0 ui: Fix spacing in tool-call request (#25634) Bill Sideris 2026-07-14 18:23:11 +03:00
  • dfba90db63 webui: parse effective-parameter sizes (E2B, E4B) as params (#25529) Emanuil Rusev 2026-07-14 18:12:22 +03:00
  • 00e79f6fb1 opencl: fix a dp4a bug for devices where cl_khr_integer_dot_product is unavailable (#25639) b10007 Hongqiang Wang 2026-07-14 08:08:13 -07:00
  • 17a05e451f ui: fix mcp panel for toggle + timeout + proxy + ON/OFF state (#25631) Pascal 2026-07-14 16:50:44 +02:00
  • 7f575c39d6 DeepseekV4: fix seq_rm (#25588) b10005 Aman Gupta 2026-07-14 21:45:36 +08:00
  • 234252e03d label virtual devices in description; add GPUx2 server CI jobs ci/cuda-virtual-devices Anav Prasad 2026-07-14 13:45:17 +00:00
  • 7cbd61002d vulkan/cpu: Support f16 as SET_ROWS src. (#25432) b10004 Jeff Bolz 2026-07-14 08:26:55 -05:00
  • 8ff8c4299d tokenize : align usage by using common args (#25516) b10003 Adrien Gallouët 2026-07-14 15:20:53 +02:00
  • a7312ae94f ggml : add a set of functions for checking contiguity of inner tensor dimensions (#25650) b10002 fairydreaming 2026-07-14 14:37:52 +02:00
  • 6554db6ed0 add link to PR xsn/server_cors_args Xuan Son Nguyen 2026-07-14 13:07:03 +02:00
  • 9562fea713 fix test Xuan Son Nguyen 2026-07-14 12:58:13 +02:00
  • e1fa323932 add tests Xuan Son Nguyen 2026-07-14 12:28:32 +02:00
  • 941011dabb add special "localhost" value Xuan Son Nguyen 2026-07-14 12:21:52 +02:00
  • 657e01125a tests: export-graph-ops: exit gracefully when called w/o arguments (#25619) b10001 Christian Kastner 2026-07-14 12:15:41 +02:00
  • 47a39665e7 ggml: uniformize im2col dst_type for all conv ops (#23660) b10000 JusteLeo 2026-07-14 12:13:13 +02:00
  • 47c786924a kleidiai : add SME2 f32 kernel (#24414) b9999 Charles Xu 2026-07-14 12:12:18 +02:00
  • c9330ed0cf ui: add reasoning effort control to mobile add sheet (#25539) Pascal 2026-07-14 12:05:40 +02:00
  • 8dff020c64 server: add --cors-* options Xuan Son Nguyen 2026-07-14 12:05:05 +02:00
  • cb489bc0fb convert_hf_to_gguf: support split MTP export for HY V3 (#25641) Thiago Padilha 2026-07-14 06:43:15 -03:00
  • ec0dbef816 arg: Flush log before exiting after usage() (#25504) b9996 Christian Kastner 2026-07-14 11:03:22 +02:00
  • c1063ac9d7 sycl: set fattn_vec_nthreads to 256 for Battlemage (#25205) b9995 Titaniumtown 2026-07-14 05:00:00 -04:00
  • 14d3ba45f3 metal : add Q2_0 support (#25419) b9994 Pasha Khosravi 2026-07-13 21:52:00 -07:00
  • 2969d6d15d model: add Hy3 (hy_v3) support with MTP speculative decoding (#25395) b9993 Satinder Grewal 2026-07-14 10:31:04 +12:00
  • 6eddde06a4 CUDA: refactor MMQ kernel configuration (#24127) b9992 Johannes Gäßler 2026-07-13 18:37:57 +02:00
  • e920c523e3 vulkan: Use native e2m1 and e4m3 conversions for mxfp4/nvfp4 (#25338) Jeff Bolz 2026-07-13 08:44:17 -05:00
  • 259ae1df8b spec: add Minimax2 eagle3 support b9990 Adrian 2026-07-13 06:22:37 -07:00
  • 4193ea697f readme : add link to maintainer PRs (#25621) Georgi Gerganov 2026-07-13 16:07:58 +03:00
  • f4253ef965 tests: Harmonize header use (#25616) b9988 Christian Kastner 2026-07-13 14:36:51 +02:00
  • ad8d821991 gguf : add tensor shape accessor (#24405) b9987 QuintinShaw 2026-07-13 18:55:15 +08:00
  • 91c631b21d chat : fix reasoning leak with force-opened bare <think> templates (#24674) b9986 Frosty40 2026-07-13 02:45:10 -05:00
  • efb3036c18 sycl: add fused top-k MoE (#25217) b9985 Frosty40 2026-07-13 01:56:41 -05:00
  • e474bba7af sycl: add Q2_K to DMMV reorder path (#25064) b9984 Todd Malsbary 2026-07-12 23:53:39 -07:00
  • 38fd5c9993 ui: Remove recommended MCP Servers + improve MCP Servers Settings UI/UX (#25535) Aleksander Grygier 2026-07-13 08:45:04 +02:00
  • 99f3dc3229 server: honour per-request reasoning_budget_tokens in chat completions (#23116) b9982 Bernard Ladenthin 2026-07-13 01:58:44 +02:00
  • 34558825a2 vendor : update cpp-httplib to 0.50.1 (#25576) b9981 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-07-12 20:10:03 -03:00
  • 8014d2cf97 server: Don't consider models with --no-mmproj-auto as multimodal (#25590) b9980 Sebastian Dröge 2026-07-13 01:48:13 +03:00
  • 4114ba18b2 mtmd: fix silent prompt truncation on embedded NUL (#25548) b9979 Pascal 2026-07-13 00:47:25 +02:00
  • 0c4fa7a989 server : evict checkpoints within min-step of each other (#25472) b9978 Aldehir Rojas 2026-07-12 15:59:14 -05:00
  • 6b4dc2116a server : fix image blocks in tool_result being dropped during Anthropic OpenAI conversion (#22536) b9977 quei 2026-07-12 23:43:51 +08:00
  • e3546c7948 Fix conditional to display 'LLAMA_SPLIT_MODE_TENSOR not implemented for architecture' message (#24926) b9976 kdkd 2026-07-11 13:03:24 -05:00
  • d72bfa38f7 gguf : reject empty metadata keys (#24917) b9975 Rohit Mahesh 2026-07-11 13:02:44 -05:00
  • 3cec3bcd16 cuda: Don't crash when querying memory on device with no free memory. (#25157) b9974 cphlipot 2026-07-11 10:13:43 -07:00
  • 13f2b28b09 DeepseekV4: clear cache only for seq rather than full (#25521) b9973 Aman Gupta 2026-07-11 23:35:45 +08:00
  • c92e806d1c server: allow stream for exec_shell_command (#25526) b9972 Xuan-Son Nguyen 2026-07-11 12:42:55 +02:00
  • ea1f7bbb5d server: refactor server_stream (#25541) b9971 Xuan-Son Nguyen 2026-07-11 12:41:47 +02:00
  • 00f5442cc4 ggml : add GGML_OP_LIGHTNING_INDEXER that implements DeepSeek V3.2/V4 lightning indexer (#24231) b9970 fairydreaming 2026-07-11 11:39:07 +02:00
  • 76f2798059 Vulkan: route large matmuls to medium tile on Adreno (#24877) b9969 Raman Shinde 2026-07-11 13:58:29 +05:30
  • 1d1d9a9ed7 opencl: add int8 dp4 dense and MoE prefill optimization for Adreno GPUs (#25537) b9968 Hongqiang Wang 2026-07-10 23:05:58 -07:00
  • 4f37f51972 server: accept null sampling params (#25538) b9967 Pascal 2026-07-10 22:07:29 +02:00
  • c749cb0417 llama : make tensor-split regex patterns static (#24710) b9966 eduardopessin 2026-07-10 18:04:12 +01:00
  • 67776eaee5 hexagon: improve ARGSORT performance for small tensors (#25512) b9965 Max Krasnyansky 2026-07-10 09:06:06 -07:00
  • 22b69b6e92 arg: prevent duplicate spec model downloads (#25527) b9964 Xuan-Son Nguyen 2026-07-10 16:53:26 +02:00
  • 3e706dd55f mtmd: deepseek-ocr v1 multi-tile (#24717) b9963 Xuan-Son Nguyen 2026-07-10 16:05:49 +02:00
  • 3203ab47a6 server : prevent LRU eviction of models still loading gg/server-fix-lru-evict-loading Georgi Gerganov 2026-07-10 16:49:57 +03:00
  • 1f66d544cb Merge branch 'master' into xsn/mtmd_ds_ocr_tiles xsn/mtmd_ds_ocr_tiles Xuan Son Nguyen 2026-07-10 15:11:44 +02:00
  • 83c7477b3f test-deepseek-ocr: relax v1 single-view tolerance; drop trailing prompt space; make DRY opt-in and n_predict model-specific (#25486) Saba Fallah 2026-07-10 15:10:58 +02:00
  • 07d9378286 feat: pre-select models in the webui using alias (#25492) felix 2026-07-10 13:04:00 +00:00
  • 9f623c683d ui: use server modalities in non-router mode (#24874) Josh Leverette 2026-07-10 08:03:52 -05:00
  • a935fbffe1 server: remove loading.html (#25500) b9960 Xuan-Son Nguyen 2026-07-10 14:42:17 +02:00
  • 65dd9133ba metal : add CONV_2D_DW (depthwise convolution) support (#21565) dev-metal Georgi Gerganov 2026-07-10 14:51:31 +03:00
  • e3ea5dea41 metal : add set_rows with src0 f16 (#25434) Georgi Gerganov 2026-07-08 16:51:31 +03:00