Skip to content

chore(deps): bump llama-cpp-spacemit in /#144

Open
dependabot[bot] wants to merge 1 commit into
masterfrom
dependabot/nix/nix-e78a7a0be3
Open

chore(deps): bump llama-cpp-spacemit in /#144
dependabot[bot] wants to merge 1 commit into
masterfrom
dependabot/nix/nix-e78a7a0be3

Conversation

@dependabot

@dependabot dependabot Bot commented on behalf of github Jul 8, 2026

Copy link
Copy Markdown
Contributor

⚠️ Dependabot is rebasing this PR ⚠️

Rebasing might not happen immediately, so don't worry if this takes some time.

Note: if you make any changes to this PR yourself, they will take precedence over the rebase.


Bumps llama-cpp-spacemit in / from v0.1.5 to v0.1.6.

Updates llama-cpp-spacemit from v0.1.5 to v0.1.6

Release notes

Sourced from llama-cpp-spacemit's releases.

v0.1.6

Bug Fixes

  • Fix SMT multimodal server crash on hybrid/recurrent models (e.g. Qwen3.5VL). Multi-turn chat aborted on turn 2 with common.cpp:1495: failed to remove sequence N with p0=M, p1=-1, because text prompt-cache reuse was applied to multimodal requests on hybrid/recurrent models whose seq_rm() can't remove a tail range outside the bounded snapshot window. Prompt-cache reuse is now disabled only for multimodal + hybrid/recurrent models; pure-attention multimodal models keep their cache reuse.

  • Remove temp-file round-trip in SMT vision encode. The preprocessed tensor is now fed to the ONNX engine directly in memory instead of via /tmp, removing a per-image disk write+read and fixing intermittent "failed to write temp file" errors on boards with a full root partition.

Commits
  • 21379f9 fix(server): fix SMT multimodal crash on hybrid-recurrent models + drop temp-...
  • 89a1d9c fix(spacemit): fix MiniCPM-V SMT multimodal inference on RISC-V (#15)
  • c0a31b5 docs(mtmd): add multimodal model development guide; slim OHOS build; disable ...
  • See full diff in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

  • @dependabot rebase will rebase this PR
  • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
  • @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
  • @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
  • @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
  • @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
  • @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
  • @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions

@dependabot dependabot Bot added dependencies Pull requests that update a dependency file nix Pull requests that update nix code labels Jul 8, 2026
@hellasbot

hellasbot commented Jul 8, 2026

Copy link
Copy Markdown

Benchmark gate for this Dependabot PR.

  • Status: neutral
  • Head: 336cbe201b73
  • PR eval: #64769
  • Baseline eval: #61185
  • PR: #144
  • Coverage: 7 of 7 benchmarks affected by this PR (by drvpath).

benchmarks completed without material regression

Metrics for benchmarks affected by this PR:

Job Metric PR Baseline Change
x86_64-linux.bench-qwen3-0-6b-vllm-rocm-gfx1151-throughput-smoke results.elapsed_time 0.432 0.426 -1.3%
x86_64-linux.bench-qwen3-0-6b-vllm-rocm-gfx1151-throughput-smoke results.requests_per_second 18.52 18.77 -1.3%
x86_64-linux.bench-qwen3-0-6b-vllm-rocm-gfx1151-throughput-smoke results.tokens_per_second 2963.7 3003.2 -1.3%

Bumps [llama-cpp-spacemit](https://github.com/spacemit-com/llama.cpp) in `/` from v0.1.5 to v0.1.6.


Updates `llama-cpp-spacemit` from v0.1.5 to v0.1.6
- [Release notes](https://github.com/spacemit-com/llama.cpp/releases)
- [Commits](spacemit-com/llama.cpp@86d4ff2...21379f9)

---
updated-dependencies:
- dependency-name: llama-cpp-spacemit
  dependency-version: 21379f9d723ccb7a0f2cc2b0b12d9f36a65ddad2
  dependency-type: direct:production
  dependency-group: nix
...

Signed-off-by: dependabot[bot] <support@github.com>
@georgewhewell
georgewhewell force-pushed the dependabot/nix/nix-e78a7a0be3 branch from 133dd57 to 336cbe2 Compare July 10, 2026 10:21
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

dependencies Pull requests that update a dependency file nix Pull requests that update nix code

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant