llama_cpp_for_radxa_dragon_.../docs
Max Krasnyansky 5d2b52d80d
hexagon: add support for basic and extended Op profiling (#22269)
* hexagon: restore HTP_OPMASK_QUEUE

* hexagon: honor OPMASK_SKIP_COMPUTE in hmx-matmul

* hex-prof: restore op profiling

* hex-prof: enable PMU

* hexagon: simplify and improve op-queuing with full profiling support

Add separate profile descriptors.

* hexagon: remove opsync and rename opmask into opstage

opsync is no longer needed since the profiler is fully async now.
opmask name was confusing and opstage is more accurate.

* hexagon: refactor opbatch queue handling

* hexagon: add iface hooks for enabling profiler from the host

Also move all the PMU setup stuff out of the hex-utils since it's not inteded for normal use.

* hexagon: make profiler mode configurable

On older devices getting PMU counters is expensive so it's now optional.

* hexagon: add support for setting profiler pmu events from env

* hexagon: simplify profiler output (no need to print buffs, etc)

* hexagon: simplify pmu counter formating

* hexagon: add a simple profile post-proc tool

* hex-prof: add support for reading logs from stdin

* hexagon: document GGML_HEXAGON_PROFILE

* hex-prof: update default width for dims field

* hex-prof: fix linter warnings and errors

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

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Update scripts/snapdragon/ggml-hexagon-profile.py

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Trivikram Reddy <tamarnat@qti.qualcomm.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2026-04-23 14:17:21 -07:00
..
android
backend hexagon: add support for basic and extended Op profiling (#22269) 2026-04-23 14:17:21 -07:00
development docs: more extensive RoPE documentation [no ci] (#21953) 2026-04-15 14:45:16 +02:00
multimodal
ops metal: Implement ROLL op (#21946) 2026-04-16 11:54:37 +03:00
android.md
autoparser.md
build-riscv64-spacemit.md
build-s390x.md
build.md CUDA: require explicit opt-in for P2P access (#21910) 2026-04-15 16:01:46 +02:00
docker.md CI : Enable CUDA and Vulkan ARM64 runners and fix CI/CD (#21122) 2026-03-30 20:24:37 +02:00
function-calling.md
install.md
llguidance.md
multimodal.md docs: listing qwen3-asr and qwen3-omni as supported (#21857) 2026-04-13 22:28:17 +02:00
ops.md metal: Implement ROLL op (#21946) 2026-04-16 11:54:37 +03:00
preset.md
speculative.md