sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 108 Packages Projects Releases Wiki Activity

Commit Graph

  • e32d243849 ai : update gh permissions (#20895) Georgi Gerganov 2026-03-23 13:21:41 +02:00
  • c44a932cf4 webui: fix --webui-config-file settings not applied on load (#20823) Pascal 2026-03-23 11:25:35 +01:00
  • 177c75852a metal: add CONV_3D (#19927) Rashid Ul Islam 2026-03-23 13:15:34 +05:30
  • 7a0b6a635e common/autoparser : detect reasoning markers when enable_thinking changes system prompt (#20859) Jhen-Jie Hong 2026-03-23 15:35:27 +08:00
  • 07ff000551 CANN: add RoPE cache preload before ACL graph capture (#20747) b8480 Chenguang Li 2026-03-23 15:24:06 +08:00
  • cc18f965b6 fix(openvino): explicit memset in buffer_context allocation (#20857) b8479 Dan Hoffman 2026-03-22 23:05:37 -07:00
  • 84ffd0c192 opencl: add flattened Q4_K mv and general Q4_K mm (#20773) b8478 shaofeiqi 2026-03-22 22:45:11 -07:00
  • ec2b787ebe mtmd: Add dynamic high-resolution image preprocessing for InternVL model (#20847) b8477 bssrdf 2026-03-22 20:06:30 -04:00
  • d3ac030a5d mtmd : fix LightOnOCR image preprocessing (#20877) b8476 DorianRudolph 2026-03-23 01:04:14 +01:00
  • 49bfddeca1 server: allow router to report child instances sleep status (#20849) b8475 Xuan-Son Nguyen 2026-03-22 18:33:52 +01:00
  • bd3f1d9d65 CUDA: fix BF16 FA compilation (#20865) b8474 Johannes Gäßler 2026-03-22 17:53:33 +01:00
  • 23c9182ce8 jinja : refactor token advancement (#20864) b8473 Sigbjørn Skjæret 2026-03-22 17:45:10 +01:00
  • 81bc4d3ddc server: fix Host header (#20843) b8472 Evgeny Kurnevsky 2026-03-22 15:29:22 +01:00
  • f40a80b4f3 support bf16 and quantized type (#20803) b8471 Neo Zhang 2026-03-22 22:06:27 +08:00
  • db9d8aa428 ggml-cuda: native bf16 flash attention for vec kernel (#20525) b8470 Patrick Buckley 2026-03-22 03:05:51 -07:00
  • ccb87fa3ee [CUDA] Increase number of output elements per-thread block if the K-dimension is small (#20635) b8469 Gaurav Garg 2026-03-22 14:19:35 +05:30
  • 3306dbaef7 misc : prefer ggml-org models in docs and examples (#20827) b8468 ddh0 2026-03-21 16:00:26 -05:00
  • 990e4d9698 common/grammar: fix grammar parsing issues to prevent stack overflow and hangs (#18604) b8467 Andrea Arcangeli 2026-03-21 13:43:35 -04:00
  • 212f4521b0 context : use n_embd_out for pooled embedding extraction (#20840) b8466 Tom Hillbrunner 2026-03-21 18:35:00 +01:00
  • 568aec82d2 docs : explicit about banning accounts that violates policy (#19593) Xuan-Son Nguyen 2026-03-21 15:50:16 +01:00
  • 2bcdddd5e3 fix(rpc): prevent division by zero in deserialize_tensor (#20712) b8464 y198 2026-03-21 20:59:43 +07:00
  • eac9c6ea83 Convert: Make NVFP4 and MXFP4 HF conversions say NVFP4/MXFP4 instead of BF16 (#20730) Michael Wand 2026-03-21 04:35:21 -07:00
  • 29b28a9824 ci : switch from pyright to ty (#20826) Sigbjørn Skjæret 2026-03-21 08:54:34 +01:00
  • cea560f483 Add shader count for Intel Arc Pro B60 (#20818) b8461 Matt Corallo 2026-03-21 04:22:51 +00:00
  • b1c70e2e54 common/parser: fix nasty bug causing subtle corruption of generation prompt (#20825) b8460 Piotr Wilkin (ilintar) 2026-03-21 00:19:04 +01:00
  • e6ec21e62f ggml-cpu: add always_inline to tinyBLAS_PPC accumulator saves (#20791) b8459 shalinib-ibm 2026-03-21 04:41:45 +05:30
  • 4cb7e0bd61 ai : limit runtime of the agent (#20816) Georgi Gerganov 2026-03-20 20:31:25 +02:00
  • 149b2493c0 common : fix typo in debug log ('extracft' -> 'extract') (#20807) b8457 James O'Leary 2026-03-20 10:23:18 -07:00
  • b31b30f31d ai : do not run bash commands in the prompt (#20810) Georgi Gerganov 2026-03-20 19:06:33 +02:00
  • 58c81f7e81 model : fix Granite Hybrid type check for 7B.A1B (#20795) Victor Villar 2026-03-20 15:16:09 +01:00
  • fb78ad29bb server: (doc) clarify in-scope and out-scope features (#20794) Xuan-Son Nguyen 2026-03-20 14:03:50 +01:00
  • e06c3ab2bc vulkan: change gated_delta_net to shard a column across a subgroup (#20662) Jeff Bolz 2026-03-20 06:17:15 -05:00
  • dc6592431b context: zero output buffer on allocation (#20781) Ruikai Peng 2026-03-20 17:31:34 +08:00
  • 3adbef7776 model: assert nextn_predict_layers to prevent underflow (#20783) Ruikai Peng 2026-03-20 17:17:58 +08:00
  • ab9d4c3678 server : improve mtmd ctx checkpoints (#20726) Georgi Gerganov 2026-03-20 11:13:12 +02:00
  • 1af9dab32b CANN: add BF16 support for core operators (#20152) hipudding 2026-03-20 17:08:39 +08:00
  • 6d99b44c7e docs : fix Metal backend op support status in ops.md (#20779) Seyoung Jeong 2026-03-20 03:06:38 -06:00
  • 464fd0e71f ai : update find-related action (#20790) Georgi Gerganov 2026-03-20 10:28:14 +02:00
  • 21c8045214 jinja : fix heap OOB read in value equality comparison (#20782) Ruikai Peng 2026-03-20 14:15:17 +08:00
  • c46583b86b common/parser : fix out_of_range crash in throw path (#20424 regression) (#20777) b8445 James O'Leary 2026-03-19 18:37:22 -07:00
  • c1b911654a server: fix router mode deadlock on child crash and TOCTOU race in models_max (#20763) Ben Racicot 2026-03-19 17:16:05 -04:00
  • b739738dad docs: Update server README to reflect PR #20297 (#20560) Tomeamis 2026-03-19 21:28:44 +01:00
  • a0bbcdd9b6 ggml: guard KleidiAI DOWNLOAD_EXTRACT_TIMESTAMP for cmake < 3.24 (#20767) Sundaram krishnan 2026-03-20 01:06:23 +05:30
  • 6c72646a61 ci : improve action for duplicate issue (#20772) Georgi Gerganov 2026-03-19 21:11:53 +02:00
  • 340807273b hip: Avoid compiler bug in RDNA code generation during debug builds on Windows (#20655) Rail Chabdarov 2026-03-19 19:14:08 +01:00
  • 26c9ce1288 server: Add cached_tokens info to oaicompat responses (#19361) Ryan Goulden 2026-03-19 11:09:33 -07:00
  • 76f2dc70c3 chat : handle tool calls with no required args in TAG_WITH_TAGGED format (#20764) James O'Leary 2026-03-19 09:53:11 -07:00
  • 900efd531d ci : clarify gh command for viewing issues (#20766) Georgi Gerganov 2026-03-19 18:43:54 +02:00
  • 74c42ee1f4 hexagon: add Matrix Extensions (HMX) for Hexagon NPU backend (#20693) Yiwei Shao 2026-03-19 09:11:06 -07:00
  • b49d8b8757 ci : add hip quality check (#20430) uvos 2026-03-19 17:05:44 +01:00
  • 5e54d51b19 common/parser: add proper reasoning tag prefill reading (#20424) Piotr Wilkin (ilintar) 2026-03-19 16:58:21 +01:00
  • c1258830b2 ggml webgpu: ops support for qwen3.5 (SET, TRI_SOLVE, SSM_CONV, GATED_DELTA_NET) + GET_ROWS optimization (#20687) Reese Levine 2026-03-19 08:45:28 -07:00
  • 922b90e567 common : add LLAMA_ARG_SPEC_TYPE (#20744) ddh0 2026-03-19 10:16:55 -05:00
  • f071ce67c9 ci : add action for finding duplicate issues (#20756) Georgi Gerganov 2026-03-19 16:17:37 +02:00
  • 4065c1a3a6 Server becomes the source of truth for sampling parameter defaults (#20558) Pascal 2026-03-19 13:20:39 +01:00
  • 1e64534570 mtmd: add clip_graph::build_mm() (#20751) b8429 Xuan-Son Nguyen 2026-03-19 13:11:39 +01:00
  • cd708db0cc WebUI: Persist the on/off state of the MCP servers for new conversations (#20750) Pascal 2026-03-19 12:54:06 +01:00
  • 512bba6ee0 webui: Improve model parsing logic + add unit tests (#20749) Aleksander Grygier 2026-03-19 12:25:50 +01:00
  • b486c17b3e convert : support is_causal hyperparameter (#20746) Dowon 2026-03-19 19:41:11 +09:00
  • 1b9bbaa357 common : fix gpt-oss content removal (#20745) b8425 Aldehir Rojas 2026-03-19 05:40:39 -05:00
  • 07feeaa92e vulkan: dequantize iq4_xs 4 at a time (#20657) b8424 Eve 2026-03-19 10:32:04 +00:00
  • 3fee84e156 cmake : fix build warning when kleidiai is enabled (#20457) b8423 Charles Xu 2026-03-19 09:14:48 +01:00
  • 811397745e vocab : assert array size of scores and toktypes (#20737) b8422 Sigbjørn Skjæret 2026-03-19 08:34:04 +01:00
  • c014c3f83a docs: add information about openvino in the docker page (#20743) Kevin Hannon 2026-03-19 03:08:47 -04:00
  • 7f2cbd9a4d CANN: handle in-place ROPE on non-contiguous f32 tensors (#20274) b8420 Chenguang Li 2026-03-19 14:05:01 +08:00
  • 509a31d00f ggml-webgpu: Update the RMS_NORM preprocessor and add L2_NORM (#20665) b8419 Masashi Yoshimura 2026-03-19 13:08:59 +09:00
  • ea01d196d7 ggml-webgpu: Add supports for DIAG and TRI (#20664) b8418 Masashi Yoshimura 2026-03-19 13:08:35 +09:00
  • 07ba6d275b CANN: support flash attention for head dim not multiple of 16, fix ALiBi slope offset (#20031) b8417 Chenguang Li 2026-03-19 11:02:42 +08:00
  • 6729d4920c model : add control vector support where missing (#20653) b8416 Michael Grau 2026-03-18 23:25:12 +01:00
  • d13d60af1d gguf-py : cleaner way to get the first key (#20727) Sigbjørn Skjæret 2026-03-18 23:21:42 +01:00
  • 5744d7ec43 Rebuild index.html.gz (#20724) crsawyer 2026-03-18 12:49:57 -05:00
  • 8ced5f41f9 Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends (#20618) b8413 Reese Levine 2026-03-18 10:23:47 -07:00
  • 78d550b541 ggml-cpu/x86: fix unused changemask warning in repack (#20692) b8412 Shaw Nguyen 2026-03-18 23:45:06 +07:00
  • 4efd326e71 sync : ggml b8411 Georgi Gerganov 2026-03-18 14:45:54 +02:00
  • b08f7322ee ggml : bump version to 0.9.8 (ggml/1442) Georgi Gerganov 2026-03-16 20:15:14 +02:00
  • 79187f2fb8 ggml : restore ggml_type_sizef() to aboid major version bump (ggml/1441) Georgi Gerganov 2026-03-16 20:09:25 +02:00
  • 48e61238e1 webui: improve tooltip wording for attachment requirements (#20688) Julien Chaumond 2026-03-18 14:01:02 +01:00
  • 312cf03328 llama : re-enable manual LoRA adapter free (#19983) b8407 Pop Flamingo 2026-03-18 11:03:26 +01:00
  • f4049ad735 tests : fix test-jinja-py Windows failures by bypassing command-line args [no ci] (#20483) Masato Nakasaka 2026-03-18 02:43:31 -07:00
  • 5e8910a0db common : rework gpt-oss parser (#20393) b8405 Aldehir Rojas 2026-03-18 04:41:25 -05:00
  • fe00a84b4b tests: enable kv_unified to prevent cuda oom error on rtx 2060 (#20645) Aaron Teo 2026-03-18 17:40:22 +08:00
  • 7ab321d40d webui: Fix duplicated messages on q param (#20715) Aleksander Grygier 2026-03-18 10:32:43 +01:00
  • 7533a7d509 HIP : ignore return of hipMemAdvise [no ci] (#20696) uvos 2026-03-18 09:53:13 +01:00
  • a69d54f990 context : fix graph not resetting when control vector changes (#20381) b8401 Andreas Obersteiner 2026-03-18 07:10:13 +01:00
  • cf23ee2447 hexagon: add neg, exp, sigmoid, softplus ops, cont, repeat ops (#20701) b8400 Krishna Sridhar 2026-03-17 15:34:36 -07:00
  • 892e3c333a vulkan: disable mmvq on Intel Windows driver (#20672) b8399 Ruben Ortlam 2026-03-17 21:51:43 +01:00
  • ee4801e5a6 ggml-blas: set mkl threads from thread context (#20602) b8398 Kevin Hannon 2026-03-17 13:16:49 -04:00
  • d2ecd2d1cf common/parser: add --skip-chat-parsing to force a pure content parser. (#20289) Piotr Wilkin (ilintar) 2026-03-17 16:16:43 +01:00
  • 054d8b0f24 ggml-cpu: fix RVV checks in quants and repacking (#20682) Taimur Ahmad 2026-03-17 19:03:40 +05:00
  • ab0bb93748 ci : bump ccache [no ci] (#20679) Sigbjørn Skjæret 2026-03-17 14:54:31 +01:00
  • 3a5cb629b1 vulkan: async and event fixes (#20518) b8394 Ruben Ortlam 2026-03-17 14:27:23 +01:00
  • 8cc2d81264 server : fix ctx checkpoint invalidation (#20671) b8393 Georgi Gerganov 2026-03-17 15:21:14 +02:00
  • 627670601a kleidiai : fix MUL_MAT support for batched (3D) inputs (#20620) b8392 Justin Bradford 2026-03-17 05:03:54 -07:00
  • 740a447fc3 vulkan: allow graphics queue only through env var (#20599) b8391 Ruben Ortlam 2026-03-17 10:09:59 +01:00
  • b6c83aad55 [SYCL] ehance UPSCALE to support all UT cases (#20637) b8390 Neo Zhang 2026-03-17 10:01:52 +08:00
  • 2e4a6edd4a tools/server: support refusal content for Responses API (#20285) b8389 Piotr Wilkin (ilintar) 2026-03-17 01:42:04 +01:00
  • d34ff7eb5b model: mistral small 4 support (#20649) b8388 Xuan-Son Nguyen 2026-03-17 00:31:14 +01:00
  • 45172df4d6 ci : disable AMX jobs (#20654) Georgi Gerganov 2026-03-16 22:38:59 +02:00
  • 9b342d0a9f benches : add Nemotron 3 Nano on DGX Spark (#20652) Georgi Gerganov 2026-03-16 21:50:43 +02:00
  • 55e87026f7 tests : write to binary buffer to avoid newline translation in jinja -py [no ci] (#20365) Sigbjørn Skjæret 2026-03-16 20:40:22 +01:00