Commit graph

Select branches

Hide pull requests

master

Mono Color

• a4f569e8a3
  [SYCL] fix no file in win rel (#6314) Neo Zhang Jianyu 2024-03-27 09:47:06 +08:00
• 32c8486e1f
  wpm : portable unicode tolower (#6305) Jared Van Bortel 2024-03-26 17:46:21 -04:00
• 557410b8f0
  llama : greatly reduce output buffer memory usage (#6122) compilade 2024-03-26 10:46:41 -04:00
• 55c1b2a3bb
  IQ1_M: 1.75 bpw quantization (#6302) Kawrakow 2024-03-26 15:21:27 +01:00
• e097633f63
  convert-hf : fix exception in sentencepiece with added tokens (#6320) Pedro Cuenca 2024-03-26 13:32:19 +01:00
• d25b1c31b0
  quantize : be able to override metadata by key (#6321) Kawrakow 2024-03-26 13:09:30 +01:00
• deb7240100
  embedding : adjust n_ubatch value (#6296) Minsoo Cheong 2024-03-26 18:11:46 +09:00
• 3d032ece8e
  server : add n_discard parameter (#6300) Jan Boon 2024-03-26 16:47:43 +08:00
• e190f1fca6
  nix: make xcrun visible in Nix sandbox for precompiling Metal shaders (#6118) Joseph Stahl 2024-03-25 20:51:46 -04:00
• 280345968d
  cuda : rename build flag to LLAMA_CUDA (#6299) slaren 2024-03-26 01:16:01 +01:00
• b06c16ef9f
  nix: fix blas support (#6281) Christian Kögler 2024-03-25 18:52:45 +01:00
• 1f2fd4e727
  tests : include IQ2_XXS and IQ2_XS in test-quantize-fns (#6303) Kawrakow 2024-03-25 18:33:15 +01:00
• 43139cc528
  flake.lock: Update (#6266) Georgi Gerganov 2024-03-25 17:22:27 +02:00
• 2f34b865b6
  cuda : fix LLAMA_CUDA_F16 build (#6298) slaren 2024-03-25 15:43:22 +01:00
• ae1f211ce2
  cuda : refactor into multiple files (#6269) slaren 2024-03-25 13:50:23 +01:00
• ad3a0505e3
  Server: clean up OAI params parsing function (#6284) Xuan Son Nguyen 2024-03-25 09:42:17 +01:00
• 95ad616cdd
  [SYCL] fix SYCL backend build on windows is break by LOG() error (#6290) Neo Zhang Jianyu 2024-03-25 15:52:41 +08:00
• 64e7b47c69
  examples : add "retrieval" (#6193) Minsoo Cheong 2024-03-25 16:38:22 +09:00
• 7733f0c760
  ggml : support AVX512VNNI (#6280) Justine Tunney 2024-03-25 01:39:56 -04:00
• a32b77c4b2
  Fix heap corruption from wmode out-of-bound writes on windows (#6272) Rick G 2024-03-24 14:45:56 -07:00
• a0e584defd
  imatrix : fix wname for mul_mat_id ops (#6271) Georgi Gerganov 2024-03-24 16:18:45 +02:00
• 7aed0ffe68
  Fixed lookup compilation issues on Windows (#6273) Johannes Gäßler 2024-03-24 14:21:17 +01:00
• ea279d5609
  ci : close inactive issue, increase operations per run (#6270) Pierrick Hymbert 2024-03-24 09:57:06 +01:00
• 586e7bc561
  sampling : deduplicated code for probability distribution access (#6240) Minsoo Cheong 2024-03-24 17:54:07 +09:00
• ddf6568510
  [SYCL] offload op (#6217) Meng, Hengyu 2024-03-24 12:04:25 +08:00
• d03224ac98
  Support build win release for SYCL (#6241) Neo Zhang Jianyu 2024-03-24 09:44:01 +08:00
• 94d1b3b411
  use _wfopen instead of fopen on Windows (#6248) Jared Van Bortel 2024-03-23 18:48:02 -04:00
• 95562175f8
  gitignore : gguf-split Georgi Gerganov 2024-03-23 21:35:23 +02:00
• f482bb2e49
  common: llama_load_model_from_url split support (#6192) Pierrick Hymbert 2024-03-23 18:07:00 +01:00
• 1997577d5e
  server: docs: --threads and --threads, --ubatch-size, --log-disable (#6254) Pierrick Hymbert 2024-03-23 18:00:38 +01:00
• 476b0251b2
  llama : add grok-1 support (#6204) Julius Arkenberg 2024-03-23 17:41:53 +01:00
• 21cad01b6e
  split: add gguf-split in the make build target (#6262) Pierrick Hymbert 2024-03-23 17:18:13 +01:00
• 1b26aebe4d
  server: flush stdout after logging in both text and json layout (#6253) Pierrick Hymbert 2024-03-23 13:18:45 +01:00
• 50ccaf5eac
  lookup: complement data from context with general text statistics (#5479) Johannes Gäßler 2024-03-23 01:24:36 +01:00
• 56a00f0a2f
  common : default --hf-file to --model (#6234) Georgi Gerganov 2024-03-22 21:10:39 +02:00
• 92397d87a4
  convert-llama2c-to-ggml : enable conversion of GQA models (#6237) fraxy-v 2024-03-22 20:49:06 +02:00
• 1d0331c12a
  quantize: options for output and token embedding tensors qtype (#6239) Kawrakow 2024-03-22 19:47:14 +01:00
• dba1af6129
  llama_model_loader: support multiple split/shard GGUFs (#6187) Pierrick Hymbert 2024-03-22 19:00:01 +01:00
• ee804f6223
  ci: apply concurrency limit for github workflows (#6243) Minsoo Cheong 2024-03-23 02:15:06 +09:00
• 80bd33bc2c
  common : add HF arg helpers (#6234) Georgi Gerganov 2024-03-22 15:33:38 +02:00
• e80f06d2a1
  llama : correction of the attn.v.weight quantization for IQ3_XS (#6209) Nexesenex 2024-03-22 14:32:02 +01:00
• f77a8ffd3b
  tests : conditional python & node json schema tests (#6207) Olivier Chafik 2024-03-22 13:09:07 +00:00
• 72114edf06
  json-schema-to-grammar : fix order of props + non-str const/enum (#6232) Olivier Chafik 2024-03-22 13:07:44 +00:00
• 2f0e81e053
  cuda : add LLAMA_CUDA_NO_PEER_COPY to workaround broken ROCm p2p copy (#6208) slaren 2024-03-22 14:05:31 +01:00
• 29ab270e65
  readme : add RecurseChat to the list of UIs (#6219) Xiaoyi Chen 2024-03-22 04:29:49 -07:00
• 6b8bb3a31d
  server : fix n_keep always showing as 0 in response (#6211) Jan Boon 2024-03-22 19:12:05 +08:00
• 68e210b354
  server : enable continuous batching by default (#6231) Georgi Gerganov 2024-03-22 13:08:28 +02:00
• b3e94f26ba
  metal : proper assert for mat-mat memory alignment (#6225) Georgi Gerganov 2024-03-22 11:35:53 +02:00
• b2075fd6a5
  ci : add CURL flag for the mac builds (#6214) Vaibhav Srivastav 2024-03-22 08:53:43 +01:00
• 95d576b48e
  metal : pad n_ctx by 32 (#6177) Georgi Gerganov 2024-03-22 09:36:03 +02:00
• 59c17f02de
  add blog link (#6222) Neo Zhang Jianyu 2024-03-22 15:19:37 +08:00
• fa046eafbc
  Fix params underscore convert to dash. (#6203) DAN™ 2024-03-21 21:32:42 -04:00
• be07a03217
  server : update readme doc from slot_id to id_slot (#6213) Jan Boon 2024-03-22 06:41:24 +08:00
• d0a71233fb
  cuda : disable host register by default (#6206) slaren 2024-03-21 19:54:28 +01:00
• f372c49ccd
  Corrected typo to wrong file (#6199) semidark 2024-03-21 11:52:35 -06:00
• 924ce1dce7
  tests : disable system() calls (#6198) Georgi Gerganov 2024-03-21 16:20:05 +02:00
• 03a8f8fafe
  cuda : fix LLAMA_CUDA_F16 build (#6197) slaren 2024-03-21 13:59:53 +01:00
• cfd3be76e3
  ggml : same IQ4_NL quantization for CPU/CUDA/Metal (#6196) Kawrakow 2024-03-21 13:59:38 +01:00
• 5b7b0ac8df
  json-schema-to-grammar improvements (+ added to server) (#5978) Olivier Chafik 2024-03-21 11:50:43 +00:00
• 1943c01981
  ci : fix indentation error (#6195) Vaibhav Srivastav 2024-03-21 10:30:40 +01:00
• 5e43ba8742
  build : add mac pre-build binaries (#6182) Vaibhav Srivastav 2024-03-21 10:13:12 +01:00
• 76aa30a263
  Add ability to use Q5_0, Q5_1, and IQ4_NL for quantized K cache (#6183) Kawrakow 2024-03-21 08:27:57 +01:00
• c5b8595e3f
  Add nvidia and amd backends (#6157) AidanBeltonS 2024-03-21 06:10:52 +00:00
• 42e21c6882
  cuda : fix conflict with std::swap (#6186) slaren 2024-03-21 01:47:46 +01:00
• 1c51f98adc
  cuda : print the returned error when CUDA initialization fails (#6185) slaren 2024-03-20 21:03:26 +01:00
• f9c7ba3447
  llava : update MobileVLM-README.md (#6180) Ziang Wu 2024-03-20 23:29:51 +08:00
• 272935b281
  llava : add MobileVLM_V2 backup (#6175) Ziang Wu 2024-03-20 23:02:32 +08:00
• ccf58aa3ec
  cuda : refactor to remove global resources (#6170) slaren 2024-03-20 14:42:59 +01:00
• 91f8ad167d
  Server: version bump for httplib and json (#6169) Xuan Son Nguyen 2024-03-20 13:30:36 +01:00
• 6b7e76d28c
  gitignore : ignore curl-related files Georgi Gerganov 2024-03-20 14:17:34 +02:00
• bc0baab2ea
  server : allow to override -ngl in tests (#6170) Georgi Gerganov 2024-03-20 14:14:32 +02:00
• d795988d9e
  Revert "llava : add a MobileVLM_V2-1.7B backup (#6152)" Georgi Gerganov 2024-03-20 13:29:49 +02:00
• f8c4e745e1
  llava : add a MobileVLM_V2-1.7B backup (#6152) Ziang Wu 2024-03-20 19:20:37 +08:00
• 47cc7a7bf9
  Server: Handle n_keep parameter in the request (#6174) Karthick 2024-03-20 16:32:34 +05:30
• bd60d82d0c
  server tests : more pythonic process management; fix bare except: (#6146) Jared Van Bortel 2024-03-20 01:33:49 -04:00
• 6c0b287748
  update readme sycl for new update (#6151) Neo Zhang Jianyu 2024-03-20 11:21:41 +08:00
• d26e8b669d
  increase igpu cluster limit (#6159) Abhilash Majumder 2024-03-20 08:28:49 +05:30
• d8b009a945
  Remove undeed header file. (#6158) DAN™ 2024-03-19 12:16:09 -04:00
• d0d5de42e5
  gguf-split: split and merge gguf per batch of tensors (#6135) Pierrick Hymbert 2024-03-19 12:05:44 +01:00
• b80cf3b2d1
  common : disable repeat penalties by default (#6127) Georgi Gerganov 2024-03-19 10:21:54 +02:00
• 970a48060a
  ci : exempt some labels from being tagged as stale (#6140) slaren 2024-03-19 09:06:54 +01:00
• 4c28b82529
  common : print usage on '-h' and '--help' (#6145) DAN™ 2024-03-19 01:59:36 -04:00
• 2d15886bb0 flake.lock: Update github-actions[bot] 2024-03-17 06:37:44 +00:00
• d199ca79f2
  mpt : implement backwards compatiblity with duped output tensor (#6139) Jared Van Bortel 2024-03-18 12:49:02 -04:00
• 104f5e0fc1
  clip : fix memory leak (#6138) Felix 2024-03-18 16:40:22 +01:00
• 5e1b7f94a0
  backend : set max split inputs to GGML_MAX_SRC (#6137) slaren 2024-03-18 16:33:44 +01:00
• ac9ee6a4ad
  ci : disable stale issue messages (#6126) Georgi Gerganov 2024-03-18 13:45:38 +02:00
• 4f6d1337ca
  ci : temporary disable sanitizer builds (#6128) Georgi Gerganov 2024-03-18 13:45:27 +02:00
• 2bf8d0f7c4
  backend : offload large batches to GPU (#6083) slaren 2024-03-18 11:03:04 +01:00
• 496bc79bc2
  common : tidy-up argument parsing (#6105) DAN™ 2024-03-18 04:27:44 -04:00
• 9b03719ad7
  convert : add support for CamembertModel architecture (#6119) Thérence 2024-03-18 09:17:00 +01:00
• 3a6efdd03c
  convert : use f32 outtype for bf16 tensors (#6106) Romain D 2024-03-18 09:04:41 +01:00
• d01b3c4c32
  common: llama_load_model_from_url using --model-url (#6098) Pierrick Hymbert 2024-03-17 19:12:37 +01:00
• cd776c37c9
  ci : close all stale issues at once (#6115) Georgi Gerganov 2024-03-17 19:51:57 +02:00
• dc0f612548
  ggml:fix finding transfer queue family index error (#6094) GainLee 2024-03-18 01:12:22 +08:00
• c47cf414ef
  ggml : add AVX512F SIMD (#6088) AmirAli Mirian 2024-03-16 11:52:02 -04:00
• b5f4ae09c3
  gritlm : add initial README.md (#6086) Daniel Bevenius 2024-03-16 16:46:29 +01:00
• dfbfdd60f9
  readme : add wllama as a wasm binding (#6100) Xuan Son Nguyen 2024-03-16 16:42:08 +01:00
• 15961ec04d
  common : refactor nested if causing error C1061 on MSVC (#6101) DAN™ 2024-03-16 11:39:15 -04:00
• a56d09a440
  ci : close inactive issue with workflow (#6053) Pierrick Hymbert 2024-03-16 13:20:53 +01:00