UPSTREAM PR #21283: [SYCL] fix llama_kv_cache hang when kv_cache is huge: 5GB#1326
Open
UPSTREAM PR #21283: [SYCL] fix llama_kv_cache hang when kv_cache is huge: 5GB#1326
Conversation
|
No meaningful performance changes were detected across 123165 analyzed functions in the following binaries: build.bin.libllama.so, build.bin.llama-bench, build.bin.libmtmd.so, build.bin.llama-cvector-generator, build.bin.llama-tts, build.bin.llama-quantize, build.bin.llama-qwen2vl-cli, build.bin.llama-tokenize, build.bin.llama-gemma3-cli, build.bin.llama-gguf-split, build.bin.llama-llava-cli, build.bin.llama-minicpmv-cli, build.bin.libggml-base.so, build.bin.libggml-cpu.so, build.bin.libggml.so. 🔎 Full breakdown: Loci Inspector |
loci-dev
force-pushed
the
main
branch
9 times, most recently
from
a8215be to
34734bc
Compare
loci-dev
force-pushed
the
main
branch
9 times, most recently
from
245e873 to
d101579
Compare
loci-dev
force-pushed
the
main
branch
3 times, most recently
from
7638ab4 to
f1b46d5
Compare
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Note
Source pull request: ggml-org/llama.cpp#21283
In llama_kv_cache, when the cache size is huge, like 5GB, the code will hang.
The root cause is the memset() can't support more than 4GB.
Verified on Arc770.