llama_cpp

Files

Alexey Kopytko 581d020b12 SYCL: implement ggml_sycl_pool_vmm (#22862 )

* SYCL: implement ggml_sycl_pool_vmm

* Add an option to bypass VMM with GGML_SYCL_DISABLE_VMM

* Clean up debugging logging

* document GGML_SYCL_DISABLE_VMM

* Multi-stream MoE optimization

* Revert "Multi-stream MoE optimization"

This reverts commit 938929c3f13a562ec67c59e87cc5d38595444cce.

* Update common.hpp

Co-authored-by: Neo Zhang <zhang.jianyu@outlook.com>

* Flip GGML_SYCL_DISABLE_VMM to GGML_SYCL_ENABLE_VMM

* add logging for GGML_SYCL_ENABLE_VMM when extension is not available (SYCL_EXT_ONEAPI_VIRTUAL_MEM macro)

* Apply suggestions from code review

Co-authored-by: Alexey Kopytko <alexey@kopytko.com>

* Apply suggestion from @sanmai

* Apply suggestion from @sanmai

---------

Co-authored-by: Neo Zhang <zhang.jianyu@outlook.com>

2026-05-26 07:59:00 +03:00

android

…

backend

SYCL: implement ggml_sycl_pool_vmm (#22862 )

2026-05-26 07:59:00 +03:00

development

docs: more extensive RoPE documentation [no ci] (#21953 )

2026-04-15 14:45:16 +02:00

multimodal

mtmd : support MiniCPM-V 4.6 (#22529 )

2026-05-06 21:54:09 +02:00