llama.cpp releases · · 2 min read

b11182

Mirrored from llama.cpp releases for archival readability. Support the source by reading on the original site.

llama : add llama_prec_policy + model-driven W4A4 path (#24364)

  • Rebase and update based on #26675

Signed-off-by: ynankani [email protected]

  • CI failure fix(launh_bounds overload on HIP) and cleanup

Signed-off-by: ynankani [email protected]

  • Address review comments

Signed-off-by: ynankani [email protected]

  • Use ggml tensor instead of name in act policy map

Signed-off-by: ynankani [email protected]

  • Address review comments and cleanup

Signed-off-by: ynankani [email protected]

  • Address review comments

Signed-off-by: ynankani [email protected]

  • Rename changes

Signed-off-by: ynankani [email protected]

  • Update ggml/src/ggml-cuda/mmq.cu

Co-authored-by: Georgi Gerganov [email protected]

  • MXFP4 dispatch changes for higher src prec

Signed-off-by: ynankani [email protected]

  • Refactor and address review comments

Signed-off-by: ynankani [email protected]

  • Updates based on review comments

Signed-off-by: ynankani [email protected]

  • Apply batched suggestions from code review

Co-authored-by: Johannes Gäßler [email protected]

  • Address review comments

Signed-off-by: ynankani [email protected]

  • Apply patch from review

Signed-off-by: ynankani [email protected]


Signed-off-by: ynankani [email protected]
Co-authored-by: Georgi Gerganov [email protected]
Co-authored-by: Johannes Gäßler [email protected]

Website:

Attestations:

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

  • DISABLED
  • openEuler x86 (310p)
  • openEuler x86 (910b, ACL Graph)
  • openEuler aarch64 (310p)
  • openEuler aarch64 (910b, ACL Graph)

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from llama.cpp releases