-
Ghost
released this
2026-07-07 16:20:31 +02:00 | 402 commits to main since this releaseStudio: account for DeepSeek-V4 compute buffer in context auto-fit (#6940)
- Studio: account for DeepSeek-V4 compute buffer in context auto-fit
DeepSeek-V4-Flash's lightning indexer plus compressed sparse attention reserve a
large context-scaling compute buffer that _compute_buffer_ctx_bytes did not model
(the KQ-mask and dequant-scratch rates both miss it, even with an f16 cache).
Measured on UD-Q4_K_XL at ub 512 it is about 65.5 GiB at 1M context, which the
mask estimate puts near 1.5 GiB, so the auto-fit kept the full 1M train context
and llama-server OOM'd allocating the ~70 GB buffer, then spilled to CPU (~4
tok/s). Add a deepseek4-gated flat plus per-token term so the fit caps the context
(about 256k on a B200) and the model stays fully on GPU.- [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Downloads
-
Source code (ZIP)
0 downloads
-
Source code (TAR.GZ)
0 downloads