Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

* upstream/HEAD:
  ci : install server kleidiai runner dependencies (ggml-org#23259)
  server-context: guarantee there is at least 1 token to decode (ggml-org#23280)
  server : print graphs reused in slot timings (ggml-org#23279)
  save-load-state : refactor tests and improve readability (ggml-org#23196)
  llama-eval : add per-task summary stats (ggml-org#23151)
  ggml-webgpu : extend GDN for K>1 (ggml-org#23299)
  [SCYL] add chapter for performance reference in SYCL.md (ggml-org#23315)
  convert : filter lora tensor names (ggml-org#23077)
  sycl: add GGML_SYCL_USE_ASYNC_MEM_OP env toggle (ggml-org#22153)
  rpc : keep last_graph_uid in the device context (ggml-org#23273)

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>
(cherry picked from commit 3c81c8d)

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

Add graphs reused counter to the per-slot timing output, printed via
llama_perf_context().

Assisted-by: llama.cpp:local pi

Co-authored-by: ggerganov <ggerganov@users.noreply.github.com>

* upstream/HEAD: (25 commits)
  metal : optimize pad + cpy (ggml-org#23354)
  snapdragon: update toolchain to v0.6 (ggml-org#23369)
  ggml-cuda: tune RDNA3 Q6_K MMVQ nwarps (ggml-org#23349)
  opencl: add MoE support for q4_k, q5_k, q6_k on Adreno (ggml-org#23303)
  hexagon: add MROPE and IMROPE support in HTP rope op (ggml-org#23317)
  refactor: Chat Screen UI rendering (ggml-org#23333)
  github: mention --log-file in issue templates (ggml-org#23277)
  common: fix --help for --verbosity (ggml-org#23278)
  common: fix --fit verbosity with --verbosity 4 (ggml-org#23282)
  convert : update mtp related help (ggml-org#23334)
  hexagon: enable support for NORM op (ggml-org#23319)
  model : clarify MTP layer comment in qwen35.cpp [no ci] (ggml-org#23338)
  llama : MTP clean-up (ggml-org#23269)
  ui: Bump packages + address build warnings (ggml-org#23300)
  ci : install libssl-dev (ggml-org#23325)
  ci : install server kleidiai runner dependencies (ggml-org#23259)
  server-context: guarantee there is at least 1 token to decode (ggml-org#23280)
  server : print graphs reused in slot timings (ggml-org#23279)
  save-load-state : refactor tests and improve readability (ggml-org#23196)
  llama-eval : add per-task summary stats (ggml-org#23151)
  ...

- ggml-cpu/ops.cpp: drop duplicate quant case labels created by the merge
  (RotorQuant PLANAR/ISO/Q1_0/TQ3_0 cases were stacked twice in switch groups)
- server-context.cpp: re-merge with codex spec-decode base + integration audio
  output; fix pre-existing ctx_tgt/ctx_dft/spec references that have no matching
  member declarations (inherited from master's partial upstream PR ggml-org#23279/ggml-org#23461
  merge) -> use ctx and the per-slot common_speculative_free path
- tests/CMakeLists.txt: drop duplicate test-llama-kv-cells registration

CPU build clean (llama-quantize/server/cli, mtmd, liquid-audio, tests).
test-llama-kv-cells passes. test-quantize-fns segfaults at tq3_0 — PRE-EXISTING
on integration (identical crash+error), tracked separately.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>