server : do not default to multiple slots with speculative decoding #17017
+14
−4
Conversation
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
|
Multiple PRs are hitting webgpu-related CI failures , perhaps there is some issue in mater branch code. |
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Nov 5, 2025
* origin/master: (21 commits) vulkan: Fix GGML_VULKAN_CHECK_RESULTS to better handle fusion (ggml-org#16919) examples(gguf): GGUF example outputs (ggml-org#17025) mtmd: allow QwenVL to process larger image by default (ggml-org#17020) server : do not default to multiple slots with speculative decoding (ggml-org#17017) mtmd: improve struct initialization (ggml-org#16981) docs: Clarify the endpoint that webui uses (ggml-org#17001) model : add openPangu-Embedded (ggml-org#16941) ggml webgpu: minor set rows optimization (ggml-org#16810) sync : ggml ggml : fix conv2d_dw SVE path (ggml/1380) CUDA: update ops.md (ggml-org#17005) opencl: update doc (ggml-org#17011) refactor: replace sprintf with snprintf for safer string handling in dump functions (ggml-org#16913) vulkan: remove the need for the dryrun (ggml-org#16826) server : do context shift only while generating (ggml-org#17000) readme : update hot topics (ggml-org#17002) ggml-cpu : bicubic interpolation (ggml-org#16891) ci : apply model label to models (ggml-org#16994) chore : fix models indent after refactor (ggml-org#16992) Fix garbled output with REPACK at high thread counts (ggml-org#16956) ...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
fix #16980
The current implementation of speculative decoding in the
llama-serverrequires a separate draftllama_contextfor each slot. Combined with the new defaults from #16736 this results in extra draft contexts being allocated, increasing memory usage.This PR updates the logic to not increase the default server slots when a draft models is specified.