hexagon: make vmem and buffer-size configurable#22487
Merged
max-krasnyansky merged 9 commits intoggml-org:masterfrom Apr 29, 2026
Merged
hexagon: make vmem and buffer-size configurable#22487max-krasnyansky merged 9 commits intoggml-org:masterfrom
max-krasnyansky merged 9 commits intoggml-org:masterfrom
Conversation
We use a sane default but it's helpful to allow for an override if needed.
… management to host
…eanup in that area
github-actions
Bot
added
script
lhez
approved these changes
Apr 28, 2026
Member
Author
|
@ggml-org/maintainers can I get a second approval please. |
ServeurpersoCom
approved these changes
Apr 29, 2026
Co-authored-by: Pascal <admin@serveurperso.com>
Member
Author
|
@lhez can you please re-approve (stale again after merging suggestions) |
lhez
approved these changes
Apr 29, 2026
tekintian
added a commit
to tekintian/llama.cpp
that referenced
this pull request
May 1, 2026
* 'master' of github.com:tekintian/llama.cpp: (659 commits) ggml-webgpu: Improve performance of mat-vec and mat-mat for MUL_MAT_ID (ggml-org#22464) Update llama-mmap to use ftello/fseeko (ggml-org#22497) common : check for null getpwuid in hf-cache (ggml-org#22550) vulkan: add get/set tensor 2d functions (ggml-org#22514) spec: fix argument typo (ggml-org#22552) ci : bump ty to 0.0.33 (ggml-org#22535) vendor : update cpp-httplib to 0.43.2 (ggml-org#22548) CUDA: fix tile FA kernel on Pascal (ggml-org#22541) scripts : add wc2wt.sh - create worktree from current HEAD (ggml-org#22513) add fast matmul iquants (ggml-org#22504) spec : fix draft model checkpoints (ggml-org#22521) spec : fix vocab compat checks in spec example (ggml-org#22426) common : do not pass prompt tokens to reasoning budget sampler (ggml-org#22488) hexagon: make vmem and buffer-size configurable (ggml-org#22487) CUDA: fuse SSM_CONV + ADD(bias) + SILU (ggml-org#22478) spec : disacard last drafted token with low prob (ggml-org#22506) sync : ggml ggml : bump version to 0.10.1 (ggml/1469) webui: fix slow mic stop and WAV encode (ggml-org#22480) ggml-cpu : disable tiled matmul on AIX to fix page boundary segfault (ggml-org#22293) ... # Conflicts: # .gitignore
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
* hexagon: allow host to set max vmem size We use a sane default but it's helpful to allow for an override if needed. * hexagon: add support for measuring vmem space and move pinned mmaping management to host * hexagon: update vmem checks to use uint64 * hexagon: bump op buffers to 16 (matches max mmaps) * hexagon: bump default vmem to 3.2GB * hexagon: add support for autodetecting vmem space and some logging cleanup in that area * hexagon: fix whitespace warnings * Update scripts/snapdragon/adb/run-cli.sh Co-authored-by: Pascal <admin@serveurperso.com> * hex-adb: fix run-completion script --------- Co-authored-by: Pascal <admin@serveurperso.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Overview
This PR adds two new knobs to the Hexagon backend
GGML_HEXAGON_VMEMAllows for overriding default VMEM limit. The default is the same as before (around 3.2GB)
If set to 0 the backend will try to measure it by pre-mmaping the buffers
GGML_HEXAGON_MBUFAllows for overriding default buffer. The default is the same as before (1GB)
This might be handy on the IOT devices where the allocator might struggle with 1GB DMA buffers
I also streamlined mapping management a bit further (pinned mappings are now managed directly by the host, etc) and updated logging in the related areas.
Requirements