LLM-Inference/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-08-12 22:31:22 +04:00
Code Issues Packages Projects Releases Wiki Activity
4,889 Commits 65 Branches 88 Tags
master
Commit Graph
22 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Charles XuandGeorgi Gerganov facb02c4c3 kleidiai : dynamic chunck-based scheduling for hybrid execution (llama/23819) 2026-06-08 14:36:36 +03:00
Charles XuandGeorgi Gerganov 750fa4ca35 ggml-cpu: use runtime SVE width in FWHT (llama/24059) 2026-06-08 14:36:36 +03:00
Charles XuandGeorgi Gerganov 254f951db8 kleidiai : update to v1.24.0 and use release archive (llama/22549) 2026-05-14 21:26:48 +03:00
Charles XuandGeorgi Gerganov fea629d00f cmake : fix build warning when kleidiai is enabled (llama/20457) 
* cmake : fix build warning when kleidiai is enabled

* remove LLAMA_ARG_THREADS from KleidiAI backend
 2026-03-29 15:04:36 +03:00
Charles XuandGeorgi Gerganov dfa6858d02 kleidiai : support for concurrent sme and neon kernel execution (llama/20070) 2026-03-16 13:10:15 +02:00
Charles XuandGeorgi Gerganov 169d723fa0 kleidiai : add sme fp16 compute path for q4_0 gemm on aarch64 (llama/20043) 2026-03-16 13:10:15 +02:00
Charles XuandGeorgi Gerganov c9955367d4 kleidiai: add and integrate SVE 256-bit vector-length kernel (llama/18458) 
* kleidiai: add and integrate SVE 256-bit vector-length kernel

* updated for review comments
 2025-12-31 17:52:09 +02:00
Charles XuandGeorgi Gerganov 3920ecce3a kleidiai: add optimized per-channel kernels for Q8_0 (llama/16993) 2025-11-17 21:05:46 +02:00
Charles XuandGeorgi Gerganov c8b2c56fd2 kleidiai: kernel interface refactoring (llama/16460) 2025-10-12 11:16:23 +03:00
Charles XuandGeorgi Gerganov 01e86b69ab kleidiai : fix work size and threads sync for fp16 (llama/16246) 2025-09-30 12:31:04 +03:00
Charles XuandGeorgi Gerganov b079d9c8b0 kleidiai: fix GGML_ASSERT(*cur_backend_id != -1) failed (llama/15614) 
* kleidiai: fix GGML_ASSERT(*cur_backend_id != -1) failed

* removes the Whisper-specific check for GET_ROWS support
 2025-09-20 13:45:27 +03:00
Charles XuandGeorgi Gerganov be2676bb1c kleidiai: generalize compute_forward_kv_cache to compute_forward_fp16 (llama/15817) 2025-09-20 13:42:50 +03:00
Charles XuandGeorgi Gerganov 74583845b6 ggml: update kleidiai to v1.13.0 (llama/15663) 2025-09-20 13:42:44 +03:00
Charles XuandGeorgi Gerganov 30cc11dc94 kleidiai: fix unsigned overflow bug (llama/15150) 
* kleidiai: fix unsigned overflow bug

* address review comments
 2025-08-18 20:30:45 +03:00
Charles XuandGeorgi Gerganov fc2ff438fd kleidiai: add support for get_rows (llama/14676) 
* kleidiai: add support for get_rows

* apply fixes based on code review

* apply more fixes based on code review
 2025-07-28 13:02:32 +03:00
Charles XuandGitHub 032697b9a8 whisper: validate get_rows support for cpu extra buffer (#3323) 2025-07-14 15:13:44 +03:00
Charles XuandGeorgi Gerganov 694f435d22 ggml: Update KleidiAI to v1.9.0 (llama/14277) 2025-06-21 07:34:17 +03:00
Charles XuandGeorgi Gerganov 4fc9c34126 ggml: Add Apple support for GGML_CPU_ALL_VARIANTS (llama/14258) 2025-06-21 07:34:17 +03:00
Charles XuandGeorgi Gerganov 518835ee56 ggml: Add Android support for GGML_CPU_ALL_VARIANTS (llama/14206) 2025-06-18 12:40:34 +03:00
Charles XuandGeorgi Gerganov dc21871fcb ggml-cpu: Add CPU backend support for KleidiAI library (llama/11390) 
* ggml-cpu: Add CPU backend support for KleidiAI library

* Add environmental variable GGML_KLEIDIAI_SME

* Add support for multithread LHS conversion

* Switch kernel selection order to dotprod and i8mm

* updates for review comments

* More updates for review comments

* Reorganize and rename KleidiAI files

* Move ggml-cpu-traits.h to source file

* Update cmake for SME build and add alignment for SME

* Remove append GGML_USE_CPU_KLEIDIAI to the GGML_CDEF_PUBLIC list
 2025-02-27 08:55:36 +02:00
Charles XuandGeorgi Gerganov e7afb2b991 ggml-cpu: cmake add arm64 cpu feature check for macos (llama/10487) 
* ggml-cpu: cmake add arm64 cpu feature check for macos

* use vmmlaq_s32 for compile option i8mm check
 2024-12-08 20:14:35 +02:00
Charles XuGeorgi GerganovDiego Devesa
 		3298916e5e backend cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels (llama/9921) 
* backend-cpu: add online flow for aarch64 Q4_0 GEMV/GEMM kernels

---------

Co-authored-by: Diego Devesa <slarengh@gmail.com>
 2024-11-20 21:00:08 +02:00