fix: drop gguf VRAM estimation (now redundant)#8325
Merged
Conversation
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
mudler
force-pushed
the
chore/drop-gguf-vram-estimation
branch
from
2a8bbc7 to
5162a40
Compare
Cleanup. This is now handled directly in llama.cpp, no need to estimate from Go. VRAM estimation in general is tricky, but llama.cpp ( https://github.com/ggml-org/llama.cpp/blob/41ea26144e55d23f37bb765f88c07588d786567f/src/llama.cpp#L168 ) lately has added an automatic "fitting" of models to VRAM, so we can drop backend-specific GGUF VRAM estimation from our code instead of trying to guess as we already enable it https://github.com/mudler/LocalAI/blob/397f7f0862d4105b874523e1a0105ae036db18ec/backend/cpp/llama-cpp/grpc-server.cpp#L393 Fixes: #8302 See: #8302 (comment)
mudler
force-pushed
the
chore/drop-gguf-vram-estimation
branch
from
ca2e280 to
a52f1d8
Compare
mudler
changed the title
localai-bot
pushed a commit
to localai-bot/LocalAI
that referenced
this pull request
Mar 25, 2026
fix: drop gguf VRAM estimation Cleanup. This is now handled directly in llama.cpp, no need to estimate from Go. VRAM estimation in general is tricky, but llama.cpp ( https://github.com/ggml-org/llama.cpp/blob/41ea26144e55d23f37bb765f88c07588d786567f/src/llama.cpp#L168 ) lately has added an automatic "fitting" of models to VRAM, so we can drop backend-specific GGUF VRAM estimation from our code instead of trying to guess as we already enable it https://github.com/mudler/LocalAI/blob/397f7f0862d4105b874523e1a0105ae036db18ec/backend/cpp/llama-cpp/grpc-server.cpp#L393 Fixes: mudler#8302 See: mudler#8302 (comment)
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
1 participant
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.
Cleanup. This is now handled directly in llama.cpp, no need to estimate from Go.
VRAM estimation in general is tricky, but llama.cpp ( https://github.com/ggml-org/llama.cpp/blob/41ea26144e55d23f37bb765f88c07588d786567f/src/llama.cpp#L168 ) lately has added an automatic "fitting" of models to VRAM, so we can drop backend-specific GGUF VRAM estimation from our code instead of trying to guess as we already enable it
LocalAI/backend/cpp/llama-cpp/grpc-server.cpp
Line 393 in 397f7f0
Fixes: #8302
See: #8302 (comment)