mozempk/ggml-org-llama-cpp-mirror
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-10-14 17:00:36 +02:00
Code Issues Packages Projects Releases Wiki Activity
11,221 Commits 856 Branches 7,967 Tags
136887b665180c13c6209a4ce0673637b6cd3afd
Commit Graph
6 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
kurquharandMax Krasnyansky 7ac59a6e3a hexagon: support tiled Q4_0 and Q8_0 GET_ROWS (#29511) 
* hexagon: support tiled Q4_0 and Q8_0 GET_ROWS

* hex-get-rows: fix macros

* hex-get-rows: use tiled HVX dequantization

Assisted-by: OpenCode

* hex-get-rows: fix register spills and clean up checks for unsupported ops

* hex-get-rows: improve dma pipeline

* hex-get-rows: improve/simplify kernel selection logic

* hex-build: reenable vectorizer, didnt notice the regression earlier in the sampler update

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
 2026-09-26 23:02:37 -07:00
kurquhar ed319febb1 hexagon: use DMA for contiguous dim1 CONCAT (#29404) 
* hexagon: use DMA for contiguous dim1 CONCAT

Assisted-by: OpenCode

* hexagon: update CONCAT DMA for DMA64

Assisted-by: OpenCode
 2026-09-24 19:03:41 -07:00
kurquharAparna M PSigbjørn SkjæretMax Krasnyansky
 		07fc586e38 hexagon: dynamic quantizer improvements (#29395) 
* hexagon: fix accuracy issue in Q8_0 N=1 MUL_MAT

* hex-quant: fix register spills

* hex-mm: use dma for all dyn.quant paths

Co-authored-by: Aparna M P <aparmp@qti.qualcomm.com>

* hex-mm: remove obsolete run_quant_task

* hex-mm: update tracing to properly wrap the events

* hex-mm: use act for activation data in all paths

* hex-mm: use act_ instead of src1_ to avoid confusion in fused kernels

* hex-mm: remove/reroute the rest of the non-DMA act (aka src1) logic

* hex-dma64: yet another pass at cleaning up the dma_addr_t casts

* Update ggml/src/ggml-hexagon/htp/matmul-ops.h

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update ggml/src/ggml-hexagon/htp/matmul-ops.c

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update ggml/src/ggml-hexagon/htp/matmul-ops.c

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

* Update ggml/src/ggml-hexagon/htp/matmul-ops.c

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

---------

Co-authored-by: Max Krasnyansky <maxk@qti.qualcomm.com>
Co-authored-by: Aparna M P <aparmp@qti.qualcomm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
 2026-09-24 11:39:28 -07:00
kurquhar 97a418bdf4 hexagon: support I32 CPY and CONT (#29379) 
Assisted-by: OpenCode
 2026-09-24 10:48:57 -07:00
kurquhar 8212c78024 test: flush status (#28352) 2026-09-24 08:29:41 -07:00
kurquharandKristopher Urquhart d7bd3bfcad snapdragon: python SDK setup (Windows) (#27903) 
* port setup-build.ps1 to setup_sdk.py, to facilitate installation of Hexagon and OpenCL SDKs on Windows

* rename setup_sdk.py -> setup-sdk.py

* flake8 fix: print() -> logger.info()

---------

Co-authored-by: Kristopher Urquhart <kurquhar@qti.qualcom.com>
 2026-08-28 14:01:59 -07:00