vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Commit graph

  • e01c67affe
         llama.vim : move info to the right of screen [no ci] (#9787) Georgi Gerganov 2024-10-21 22:52:22 +03:00
  • 9415a9cb15
         Merge 865ccb4e36 into 994cfb1acb Xuan Son Nguyen 2024-10-21 20:59:39 +02:00
  • a98d4e8ee8
         fixup: add missing excution-charset 蕭澧邦 2024-10-22 02:46:52 +08:00
  • 994cfb1acb
         readme : update UI list (#9972) Asghar Ghorbani 2024-10-21 20:20:59 +02:00
  • 94008cc760
         arg : fix attention non-causal arg value hint (#9985) b3952 Daniel Bevenius 2024-10-21 20:12:52 +02:00
  • a5113451a3
         test: force source-charset to utf-8 in MSVC 蕭澧邦 2024-10-22 01:58:07 +08:00
  • dbd5f2f573
         llama.vim : plugin for Neovim (#9787) Georgi Gerganov 2024-10-21 20:25:02 +03:00
  • 8218456596 arg : fix attention non-causal arg value hint Daniel Bevenius 2024-10-21 18:35:38 +02:00
  • 89c533af18
         cmake: exclude math library when generator is Visual Studio 蕭澧邦 2024-10-22 00:20:04 +08:00
  • 5d4ace6417 test: convert test-grammar-integration.cpp to UTF-8-BOM encoding 蕭澧邦 2024-10-21 23:11:35 +08:00
  • f594bc80ba
         ggml : add asserts for type conversion in fattn kernels (#9971) b3950 Georgi Gerganov 2024-10-21 16:20:46 +03:00
  • 8fb5154547
         llama.vim : minor [no ci] Georgi Gerganov 2024-10-21 15:57:15 +03:00
  • 4d4ae1c9a1 Fix the Bug: inference running result is garbled in debug running model for LM models who's type is Q4_0 class leo-pony 2024-10-21 19:13:21 +08:00
  • d5ebd79c76
         rpc : pack only RPC structs (#9959) b3949 Radoslav Gerganov 2024-10-21 13:35:40 +03:00
  • 32927e68b7
         llama.vim : remove on-hold code + fixes [no ci] Georgi Gerganov 2024-10-21 12:32:38 +03:00
  • 8c7c04e896
         [SYCL] Fix build on Windows when ccache enabled (#9954) 蕭澧邦 2024-10-21 16:53:33 +08:00
  • a74dd353dd RWKV v6: Set EOT token to `\n\n` Molly Sophia 2024-10-21 16:30:27 +08:00
  • 95e25a6c1f RWKV: Fix the chat template not being used Molly Sophia 2024-10-21 16:29:56 +08:00
  • b8efb0725d
         llama.vim : minor [no ci] Georgi Gerganov 2024-10-18 22:45:23 +03:00
  • fe78c39399
         llama.vim : fix large chunk accept + comments [no ci] Georgi Gerganov 2024-10-18 13:48:00 +03:00
  • 6bb6e6dd80
         llama.vim : display ring capacity [no ci] Georgi Gerganov 2024-10-18 09:47:14 +03:00
  • 1600d846b6
         llama.vim : complete only whithin the local scope [no ci] Georgi Gerganov 2024-10-17 22:09:47 +03:00
  • d1b8b215d5
         llama.vim : fix repetitions of existing text Georgi Gerganov 2024-10-17 16:16:19 +03:00
  • 4583aef12b
         llama.vim : final touches Georgi Gerganov 2024-10-15 17:18:32 +03:00
  • 847c8c023e
         llama.vim : update infill API params [no ci] Georgi Gerganov 2024-10-15 11:49:20 +03:00
  • 060573f7e8
         llama.vim : add comments [no ci] Georgi Gerganov 2024-10-15 11:34:32 +03:00
  • 42a9008b31
         llama.vim : process extra chunks in the background [no ci] Georgi Gerganov 2024-10-15 10:50:18 +03:00
  • 0c1f51b73e
         llama : improve infill sampler Georgi Gerganov 2024-10-15 09:37:26 +03:00
  • e4be74b4b7
         llama.vim : add top_p + improve responsivness + fix edge cases Georgi Gerganov 2024-10-15 09:34:26 +03:00
  • 25ecb35c4f
         llama.vim : simplify job logic + improve robustness and responsivness Georgi Gerganov 2024-10-14 15:50:08 +03:00
  • 9f8fa900f6
         llama.vim : fix repetitions [no ci] Georgi Gerganov 2024-10-13 21:56:29 +03:00
  • ae76a092b8
         llama.vim : pass filenames for each chunk Georgi Gerganov 2024-10-13 21:36:02 +03:00
  • 916c2ee3fd
         llama : simplify infill sampler Georgi Gerganov 2024-10-13 18:50:36 +03:00
  • bc2857b88c
         llama.vim : async context processing Georgi Gerganov 2024-10-13 18:23:22 +03:00
  • 2960510153
         llama.vim : do not auto-fim when far from the end of the line [no ci] Georgi Gerganov 2024-10-13 17:17:01 +03:00
  • d81a0ac185
         llama.vim : do not evict certain chunks [no ci] Georgi Gerganov 2024-10-13 16:53:32 +03:00
  • 27d53cb4ee
         llama.vim : logic to evict old chunks that are similar to new one Georgi Gerganov 2024-10-13 16:11:38 +03:00
  • f794549bae
         llama.vim : gather chunk on leaving buffer [no ci] Georgi Gerganov 2024-10-13 14:17:58 +03:00
  • 27bc11da0f
         llama.vim : update server command [no ci] Georgi Gerganov 2024-10-13 13:57:19 +03:00
  • b8890229b6
         llama.vim : add ring context from opened files and yanked text Georgi Gerganov 2024-10-13 13:42:56 +03:00
  • 4f46e29b09
         llama : print more info about control tokens Georgi Gerganov 2024-10-13 13:42:16 +03:00
  • 491f211b4c
         llama : improve infill sampler Georgi Gerganov 2024-10-11 21:14:47 +03:00
  • 5624e919df
         llama.vim : fix docs [no ci] Georgi Gerganov 2024-10-11 19:39:44 +03:00
  • c9a46f4bd7
         llama.vim : minor [no ci] Georgi Gerganov 2024-10-11 13:36:56 +03:00
  • 865d9bc48a
         llama : clean-up Georgi Gerganov 2024-10-11 12:26:22 +03:00
  • 4b1bd81661
         llama : simplify infill sampler Georgi Gerganov 2024-10-10 20:36:25 +03:00
  • 2e8c350a5f
         llama.vim : fix edge cases Georgi Gerganov 2024-10-10 18:31:46 +03:00
  • 6669b550db
         llama.vim : set time limit for the generation phase Georgi Gerganov 2024-10-10 17:06:50 +03:00
  • c507a65af5
         llama.vim : async Georgi Gerganov 2024-10-10 12:27:34 +03:00
  • 41053f92d3
         llama.vim : simplify init and cancel + auto-fim Georgi Gerganov 2024-10-10 08:38:57 +03:00
  • 7e0b5062af
         llama.vim : reduce scope of ids to local [no ci] Georgi Gerganov 2024-10-09 16:07:24 +03:00
  • 26a0c61e8a
         llama.vim : allow repeated suggestions [no ci] Georgi Gerganov 2024-10-09 15:44:14 +03:00
  • 6e82a03b9d
         llama.vim : display realtime [no ci] Georgi Gerganov 2024-10-09 15:26:19 +03:00
  • 9d13e87b1b
         llama.vim : add processing info overlay Georgi Gerganov 2024-10-09 15:08:31 +03:00
  • 07e7dd47f2
         llama.vim : handle space Georgi Gerganov 2024-10-09 12:57:44 +03:00
  • 0c649c8967
         llama.vim : fix suffix construction + fix virt text offset Georgi Gerganov 2024-10-09 12:36:56 +03:00
  • 0566c69531
         llama.vim : neovim plugin Georgi Gerganov 2024-10-09 11:01:30 +03:00
  • 5aaf24766a
         llama : add infill sampler Georgi Gerganov 2024-10-09 11:01:53 +03:00
  • 4243abc143
         Update README.md Asghar Ghorbani 2024-10-21 09:59:31 +02:00
  • 55e47786e3
         llama : default sampling changes + greedy update (#9897) b3948 Georgi Gerganov 2024-10-21 09:46:40 +03:00
  • bc21975084
         speculative : fix handling of some input params (#9963) b3947 Georgi Gerganov 2024-10-21 09:37:12 +03:00
  • 1db8c84fc6
         fix mul_mat_vec_q and *_vec_q error (#9939) b3946 Neo Zhang Jianyu 2024-10-21 14:26:09 +08:00
  • 82da9efc02
         ggml : add asserts for type conversion in fattn kernels Georgi Gerganov 2024-10-21 09:00:57 +03:00
  • 1657447b2b [CANN] Adapt to dynamically loadable backends mechanism leo-pony 2024-10-21 11:26:30 +08:00
  • afb1fd7523 use GGML_LOG_* replace fprintf arthw 2024-10-21 10:16:28 +08:00
  • 738c166112 Add chat template for RWKV-World Molly Sophia 2024-10-21 09:34:56 +08:00
  • e81462dda1 remove trailing whitespaces Junhee Yoo 2024-10-21 09:28:13 +09:00
  • 413a19e25c Auto stash before rebase of "llamacasuallm-sp-bpe" onto "master" Roberto Tomás Collins 2024-10-20 20:23:36 -04:00
  • c3363f62bc line endings check in PR Roberto Tomás Collins 2024-10-20 19:03:57 -04:00
  • bd697ca77d llama : fix empty batch cause llama_batch_allocr to crash Xuan Son Nguyen 2024-10-21 00:09:56 +02:00
  • d89f49b0ee Merge remote-tracking branch 'origin/llamacasuallm-sp-bpe' into llamacasuallm-sp-bpe Roberto Tomás Collins 2024-10-20 14:25:02 -04:00
  • ff906dca42 basic concept Roberto Tomás Collins 2024-10-17 23:10:54 -04:00
  • 90ab8a10d5
         speculative : limit batch size to llama_n_batch Georgi Gerganov 2024-10-20 20:15:59 +03:00
  • 67d18498d3
         speculative : handle params.n_predict == -1 Georgi Gerganov 2024-10-20 20:10:03 +03:00
  • 47bb241cb1
         speculative : fix batch sizes at initialization Georgi Gerganov 2024-10-20 19:37:42 +03:00
  • 45f097645e
         readme : update bindings list (#9951) Loïc Carrère 2024-10-20 18:25:41 +02:00
  • 7cab2083c7
         readme : update infra list (#9942) icppWorld 2024-10-20 12:01:34 -04:00
  • a1b970550b rpc : pack only RPC structs Radoslav Gerganov 2024-10-20 10:23:57 +03:00
  • adacea9901 rm empty line' arthw 2024-10-20 10:58:40 +08:00
  • 6aa623d363 add print cpu info arthw 2024-10-20 10:47:16 +08:00
  • 8233009d4d Support SYCL device register support_device_reg arthw 2024-10-20 10:06:51 +08:00
  • d8cb5d2040 flake.lock: Update github-actions[bot] 2024-10-20 00:22:59 +00:00
  • 1494ffa901
         Merge 8b0d3ab5ab into cda0e4b648 Alexey Parfenov 2024-10-19 21:45:16 +01:00
  • 9bfecf4294 ggml : RISC-V vector gemv for q4_0_8x8 Xiongchuan Tan 2024-10-20 01:15:42 +08:00
  • a8e48e3b4c Merge remote-tracking branch 'origin/llamacasuallm-sp-bpe' into llamacasuallm-sp-bpe Roberto Tomás Collins 2024-10-19 08:30:26 -04:00
  • 730756f9df basic concept Roberto Tomás Collins 2024-10-17 23:10:54 -04:00
  • b3ca1f11ed
         Update README.md Loïc Carrère 2024-10-19 13:21:29 +02:00
  • 761384ac80 llama : rename batch to ubatch Daniel Bevenius 2024-10-19 06:13:20 +02:00
  • 14014fd109 lora : warn user if new token is added in the adapter Xuan Son Nguyen 2024-10-18 23:39:33 +02:00
  • cda0e4b648
         llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745) b3943 Xuan Son Nguyen 2024-10-18 23:18:01 +02:00
  • 2810c1bc2f Merge branch 'master' into fix_quantize_leave_output_tensor drollings 2024-10-18 16:01:50 -05:00
  • 11c29ee602 rpc : backend refactoring (#9912) Radoslav Gerganov 2024-10-18 14:33:58 +03:00
  • be19a9e1ef [SYCL] Add SYCL Backend registry, device and Event Interfaces (#9705) Ouadie EL FAROUKI 2024-10-18 06:46:16 +01:00
  • 57fecc1562 add amx kernel for gemm (#8998) Ma Mingfei 2024-10-18 13:34:36 +08:00
  • 224720ed4d server : add n_indent parameter for line indentation requirement (#9929) Georgi Gerganov 2024-10-18 07:32:19 +03:00
  • 14a199eb68 llama : rename batch_all to batch (#8881) Daniel Bevenius 2024-10-18 01:41:51 +02:00
  • 4860058e49 readme : remove --memory-f32 references (#9925) Georgi Gerganov 2024-10-17 23:43:05 +03:00
  • f7228b7fde llama : change warning to debug log Georgi Gerganov 2024-10-17 23:26:32 +03:00
  • b440d0322f llama : infill sampling handle very long tokens (#9924) Georgi Gerganov 2024-10-17 22:32:47 +03:00
  • cba857cded readme : update bindings list (#9918) Tim Wang 2024-10-17 17:57:14 +11:00