Support -fa auto in llama-bench#23714
Merged
Merged
Conversation
Make the default value of `-ngl` -1, similar to other tools. Update README with latest usage and examples
Contributor
JohannesGaessler
left a comment
JohannesGaessler
left a comment
There was a problem hiding this comment.
My opinion is that we should just change the llama-bench default to LLAMA_FLASH_ATTN_TYPE_AUTO to be consistent with the rest of the codebase.
Contributor
Author
Sure, made it the default now. |
JohannesGaessler
approved these changes
May 28, 2026
Contributor
Author
|
Thanks @JohannesGaessler . @ggerganov could you please take a look as well? To give you some background. Request for some of these changes is coming from our automation team, which is using |
Contributor
Author
|
@ggml-org/maintainers, can I get second approval, please? |
pwilkin
approved these changes
May 30, 2026
o7si
added a commit
to o7si/llama.cpp
that referenced
this pull request
May 31, 2026
…wercase * upstream/master: (27 commits) vocab : add tokenizer support for jina-embeddings-v2-base-zh (ggml-org#18756) ui: fix ETag truncation with MSVC compiler (ggml-org#23917) docs : update ZenDNN docs for Q8 support (ggml-org#23791) llama: only use one iGPU device by default (ggml-org#23897) webui: add custom CSS injection via config (ggml-org#23904) Support `-fa auto` in llama-bench (ggml-org#23714) opencl: support bf16 by converting to f16 (ggml-org#23839) ui: exclude generated build dirs from prettier and eslint so lint errors stop being masked (ggml-org#23910) TP: fix granularity for Qwen 3.5/3.6 + 3 GPUs (ggml-org#23843) metal : restore im2col implementation for large kernels (ggml-org#23901) test: (test-llama-archs) log the config name first (ggml-org#23885) ci : update ios-xcode release job to macos-26 (ggml-org#23906) ggml : add some lsx support (ggml-org#23798) vulkan: add Flash Attention support for BFloat16 KV cache (ggml-org#23420) ci : fix s390x release job (ggml-org#23898) ci : clear cache instead of "no timestamp" keys + fix macos (ggml-org#23895) llama : do not skip iGPU when only RPC devices are present (ggml-org#23868) server: in SSE mode, send HTTP headers when slot starts (ggml-org#23884) ggml-webgpu: Check earlier for WebGPU required features (ggml-org#23879) ggml-webgpu: add q4_0/q8_0 SET_ROWS (ggml-org#23760) ... # Conflicts: # gguf-py/gguf/vocab.py # src/llama-vocab.cpp
turbo-tan
pushed a commit
to turbo-tan/llama.cpp-tq3
that referenced
this pull request
Jun 2, 2026
* Support `-fa auto` in llama-bench Make the default value of `-ngl` -1, similar to other tools. Update README with latest usage and examples * Address review comments
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.
Support
-fa on|off|autoinllama-bench, similar to other tools. The default is still kept as-fa offnot to change the existing behavior, but using-fa autoallows enablingllama-serverandllama-clibehavior inllama-bench.Make the default value of
-ngl-1, similar to other tools. For most models, this won't have any impact as the previous default was 99.Update README with the latest usage and examples.
Requirements