Commit Graph

  • 935cad6497 llama : move n_vocab from llama_sampler_data to penalty_sampler (#26520) b10258 Oliver Simons 2026-08-04 08:02:49 +02:00
  • 22dc605c4e ci: fix vulkan llvmpipe runs (#26533) b10257 Eve 2026-08-04 03:28:57 +00:00
  • 6c8dcaa7ae sycl: parallelize the non-contiguous concat kernel (#25852) b10256 Titaniumtown 2026-08-03 19:08:05 -07:00
  • 66fa168a56 Extended SYCL oneDNN SDPA to non-FP16 KV caches (Q4_0–Q8_0 and FP32) (#25874) b10255 Ozymandias_EBON 2026-08-03 21:07:23 -05:00
  • 0ef6e55edb chat : add new template for DeepSeek V4 Flash 0731 (#26398) b10254 Thiago Padilha 2026-08-03 19:59:11 -03:00
  • 94bc47f280 vendor : update cpp-httplib to 0.52.0 (#26485) b10253 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-03 19:30:42 -03:00
  • 2f40d38c7c Merge branch 'master' into xsn/qwen3-tts Xuan Son Nguyen 2026-08-03 23:27:19 +02:00
  • 564f25d73a mtmd_helper_model_can_chat Xuan Son Nguyen 2026-08-03 23:26:44 +02:00
  • 2690f91b0b add step_prompt() Xuan Son Nguyen 2026-08-03 21:28:21 +02:00
  • ee1a7295dc add seq_id Xuan Son Nguyen 2026-08-03 21:13:59 +02:00
  • fe2adf0e72 vendor : update BoringSSL to 0.20260803.0 (#26523) b10252 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-03 15:31:15 -03:00
  • 57c092139a model : support MTP in GLM-4.7-Flash (#24868) b10251 jacekpoplawski 2026-08-03 20:27:52 +02:00
  • 5114c2adbb py: fix type check Xuan Son Nguyen 2026-08-03 19:03:30 +02:00
  • ee0445c99c tests: add model resolution test on synthetic repo listings (#26172) b10250 Pascal 2026-08-03 18:58:15 +02:00
  • 74b1f5f5aa adapt get_info Xuan Son Nguyen 2026-08-03 18:57:08 +02:00
  • 164f47706a Merge branch 'master' into xsn/server_docker_isolate Xuan Son Nguyen 2026-08-03 18:53:37 +02:00
  • 7e565b10f7 Merge branch 'master' into xsn/server_docker_isolate Xuan Son Nguyen 2026-08-03 18:52:40 +02:00
  • 99111b19ce server: add get_info tool (#26522) b10249 Xuan-Son Nguyen 2026-08-03 18:51:02 +02:00
  • 3dfb7c7fad server: simplify get_info result handling xsn/tool_sys_info Pascal 2026-08-03 18:22:56 +02:00
  • c74747ce8f server: harden get_info probe result handling Pascal 2026-08-03 18:16:50 +02:00
  • 5f0af44fe1 fix --rpc in docs Xuan Son Nguyen 2026-08-03 17:56:11 +02:00
  • e8e06f78e2 vocab : validate default special token ids (#26506) b10248 Sigbjørn Skjæret 2026-08-03 17:40:53 +02:00
  • 371e8b0a8c server: add get_info tool Xuan Son Nguyen 2026-08-03 17:35:02 +02:00
  • dbadb68eec ggml: use dynamic allocation for split graph inputs (#22789) b10247 AgoraPete 2026-08-03 17:03:14 +02:00
  • 39eab74a05 opencl: route large q6_K lm_head to the flat GEMV (#26427) b10246 Hongqiang Wang 2026-08-03 07:36:19 -07:00
  • c50b34a1e0 graph : fix unused input tensors in minimax m3 graph (#26519) b10245 Georgi Gerganov 2026-08-03 17:32:01 +03:00
  • 67d5978bb1 model: M3: Move MSA into a new memory implementation (#26338) b10244 timkhronos 2026-08-03 15:30:08 +02:00
  • 563dec81c1 llama : allocate indexer cache only in "full" indexer layers (#26474) b10243 fairydreaming 2026-08-03 14:56:30 +02:00
  • 96278e39fc CUDA: Add backend sampler for penalties sampler (#25262) b10242 Konrad Moren 2026-08-03 14:26:09 +02:00
  • 9bd4c09ea5 CUDA: Fix data-races when reusing SMEM in block_reduce (#26385) b10241 Oliver Simons 2026-08-03 14:22:44 +02:00
  • 0b14b87d7c server: add notice for upcoming default port change 8080 --> 9931 (#26508) b10240 Xuan-Son Nguyen 2026-08-03 12:45:24 +02:00
  • 7f5903206c correct to 9931 xsn/server_notice_port8080 Xuan Son Nguyen 2026-08-03 12:18:50 +02:00
  • 41a95911b7 add link to PR Xuan Son Nguyen 2026-08-03 12:14:24 +02:00
  • f25ff5fffe server: add notice for upcoming default port change 8080 --> 6631 Xuan Son Nguyen 2026-08-03 12:10:14 +02:00
  • ea1abe6f43 add docs Xuan Son Nguyen 2026-08-03 11:52:08 +02:00
  • 2cc28a7179 server: add initial tool isolation support (via docker) Xuan Son Nguyen 2026-08-03 11:48:06 +02:00
  • f2b52a87e8 server: (tools) add x-tool-cwd header (#26420) Xuan-Son Nguyen 2026-08-03 10:47:21 +02:00
  • 4ed2b13f75 model: MTP support for Qwen3-Next (#25589) b10238 Masashi Yoshimura 2026-08-03 17:15:01 +09:00
  • 2b63e0610b llama : MTP support for DeepSeek V3.2 (#26457) b10237 fairydreaming 2026-08-03 08:25:01 +02:00
  • 1464c62d88 metal: implement DSv4 Lightning Indexer (#25893) b10236 Thiago Padilha 2026-08-03 01:33:37 -03:00
  • 127db3f0ab clean up tts.cpp Xuan Son Nguyen 2026-08-03 01:38:41 +02:00
  • 2f240361fd clean up Xuan Son Nguyen 2026-08-03 00:16:40 +02:00
  • d827cdedcf rename CODE2WAV --> GEN_WAV, update docs Xuan Son Nguyen 2026-08-03 00:13:25 +02:00
  • 1df59d388e use ISO 639-1 language code Xuan Son Nguyen 2026-08-03 00:01:56 +02:00
  • 0b6e340205 Merge branch 'master' into xsn/qwen3-tts Xuan Son Nguyen 2026-08-02 23:55:38 +02:00
  • 221f0f6356 metal : add SILU_BACK (#25982) b10235 Talha Adnan 2026-08-02 14:39:28 -05:00
  • 9d21b57f2e metal : add F16 support for bin ops (#26465) b10234 Georgi Gerganov 2026-08-02 22:28:17 +03:00
  • 0ab9d6fed7 opencl: limit local workgroup size for GLU operation (#26383) b10233 mgroeber9110 2026-08-02 20:44:00 +02:00
  • ddd9cdb158 reuse str_to_lower from server-models xsn/tool_cwd Xuan Son Nguyen 2026-08-02 20:41:31 +02:00
  • fffbcbdb9d metal: implement DeepSeek V4 hyper-connections (#26459) b10232 Georgi Gerganov 2026-08-02 21:06:02 +03:00
  • bb4e0e1b3f common: support the DSpark sidecar resolution (#26458) b10231 Pascal 2026-08-02 19:25:27 +02:00
  • 3581ba0cf5 convert: add option to create separate dspark GGUF (#26452) Aman Gupta 2026-08-02 23:16:31 +08:00
  • 1e95e764b1 fix convert bug pr/26452 Aman Gupta 2026-08-02 22:35:46 +08:00
  • 05491879eb add --no-nextn Aman Gupta 2026-08-02 22:10:55 +08:00
  • c745be2a2c opencl: bugfix increment ref_count in ggml_backend_opencl_init() (#26162) b10229 akleine 2026-08-02 15:43:00 +02:00
  • 1445ea2993 convert: add option to create separate dspark GGUF Aman Gupta 2026-08-02 21:38:12 +08:00
  • 596a5795bd DeepseekV4 MTP + DSpark (#25784) b10228 Aman Gupta 2026-08-02 20:55:34 +08:00
  • f5919bf458 chat : add qwen3 specialized parser (#26252) b10227 Aldehir Rojas 2026-08-02 04:13:20 -05:00
  • 272700b360 sycl: fix classification of iGPUs (#26105) b10226 KyleHagy 2026-08-02 00:10:32 -07:00
  • 75587a05b3 model : load MiMo V2 MTP tensors only if used (#26412) b10225 Sigbjørn Skjæret 2026-08-02 09:03:05 +02:00
  • 7a2db1a0cf ggml-webgpu: add support for f16 repeat (#26307) b10224 Masashi Yoshimura 2026-08-02 15:28:31 +09:00
  • 9da937689f server: (tools) add x-tool-cwd header Xuan Son Nguyen 2026-08-02 01:19:30 +02:00
  • 11924d4c17 test: fix some CI errors (#26415) b10223 Xuan-Son Nguyen 2026-08-02 00:16:29 +02:00
  • a850ca8c62 test: fix some CI errors xsn/fix_ci_2 Xuan Son Nguyen 2026-08-01 23:15:10 +02:00
  • a7a6d0d269 vulkan: extend topk_moe fusion to support sqrt(softplus) (#26124) Jeff Bolz 2026-08-01 14:18:07 -05:00
  • 815a2a5915 vendor : update BoringSSL to 0.20260730.0 (#26353) b10221 Alessandro de Oliveira Faria (A.K.A.CABELO) 2026-08-01 15:53:00 -03:00
  • 6e4da4a745 Merge branch 'master' into xsn/qwen3-tts Xuan Son Nguyen 2026-08-01 19:02:46 +02:00
  • dc5dd58bea fix ci Xuan Son Nguyen 2026-08-01 19:02:42 +02:00
  • 2307bf5a4d use ggml_build_forward_select, clean up comments Xuan Son Nguyen 2026-08-01 18:50:12 +02:00
  • 89482bd665 agents: clarify comment style and jinja knowledge (#26405) Xuan-Son Nguyen 2026-08-01 18:45:46 +02:00
  • 026d35cfc8 update docs Xuan Son Nguyen 2026-08-01 18:26:59 +02:00
  • 4a9e349f63 security fixes Xuan Son Nguyen 2026-08-01 18:10:40 +02:00
  • c629da565c cli : persist reasoning_content in chat history (#26362) b10219 Nico 2026-08-01 12:03:32 -04:00
  • 37e22b750e improve Security review a bit xsn/update_agents_md Xuan Son Nguyen 2026-08-01 17:48:31 +02:00
  • b2e895327e agents: clarify comment style and jinja knowledge Xuan Son Nguyen 2026-08-01 17:39:51 +02:00
  • f695c2226c Merge branch 'master' into xsn/qwen3-tts Xuan Son Nguyen 2026-08-01 17:03:21 +02:00
  • e298a2e463 clean up code comments Xuan Son Nguyen 2026-08-01 17:02:28 +02:00
  • 8a40209704 more timings info Xuan Son Nguyen 2026-08-01 16:43:02 +02:00
  • 4523db999e add guide + docs Xuan Son Nguyen 2026-08-01 16:35:17 +02:00
  • bfc0714ad3 nits Xuan Son Nguyen 2026-08-01 16:13:06 +02:00
  • 511cc2fa0d fix lint Xuan Son Nguyen 2026-08-01 15:41:58 +02:00
  • 82dc811a6e fix compile Xuan Son Nguyen 2026-08-01 15:38:27 +02:00
  • bd52f3606f update docs Xuan Son Nguyen 2026-08-01 15:38:16 +02:00
  • 8f94fc5267 revamp llama-tts binary Xuan Son Nguyen 2026-08-01 15:33:14 +02:00
  • 22bc9df347 polymorphism helper Xuan Son Nguyen 2026-08-01 15:09:29 +02:00
  • 86020c467a update dev docs Xuan Son Nguyen 2026-08-01 15:07:28 +02:00
  • eae9c2c3f5 demo: use proper sampling Xuan Son Nguyen 2026-08-01 14:42:10 +02:00
  • de699957b9 mtmd: add minicpmv46 downsample (#25993) b10218 tc-mb 2026-08-01 19:38:36 +08:00
  • 06aae58899 fuse snake op Xuan Son Nguyen 2026-08-01 13:16:29 +02:00
  • 914fd950a3 fix clamp cold prefix Xuan Son Nguyen 2026-08-01 12:33:52 +02:00
  • ddd4ec1428 chat : enable tool call in thinking for DS4 (#26269) b10217 Piotr Wilkin (ilintar) 2026-08-01 07:13:07 +02:00
  • ffe530beb8 mtmd_helper_gen_audio API Xuan Son Nguyen 2026-08-01 00:37:00 +02:00
  • 1f096f4ade llama: add llama_model_get_tok_embd Xuan Son Nguyen 2026-07-31 22:49:52 +02:00
  • 3e9e484919 demo voice clone Xuan Son Nguyen 2026-07-31 21:56:22 +02:00
  • a9df03d08e code2wav preserve kv between calls Xuan Son Nguyen 2026-07-31 19:59:41 +02:00
  • 2348de100f demo (to be removed) Xuan Son Nguyen 2026-07-31 18:39:44 +02:00
  • 51027785e9 wip, correct code2wav Xuan Son Nguyen 2026-07-31 17:00:17 +02:00
  • 876a432116 vulkan: add POOL_1D op (#25431) b10216 Anand Patil 2026-07-31 09:48:58 -05:00
  • 13bfdc667b wire up Xuan Son Nguyen 2026-07-31 16:45:20 +02:00
  • eb41d503ba vulkan: Introduce driver version check for Windows Intel GPU to mitigate crashing (#25192) b10215 Masato Nakasaka 2026-07-31 23:26:37 +09:00