Skip to content

Releases: ggml-org/llama.cpp

b9245

20 May 04:13
@github-actions github-actions
b9245
b39a7bf
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9245 Latest
Latest

ggml-cuda: tune RDNA3 Q6_K MMVQ nwarps (#23349)

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Assets 30

b9244

20 May 03:39
@github-actions github-actions
b9244
b28a2f3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9244

opencl: add MoE support for q4_k, q5_k, q6_k on Adreno (#23303)

  • opencl: add q4_k moe support

  • opencl: add q5_k moe support

  • opencl: add q6_k moe support

  • opencl: adjust format

Co-authored-by: Li He lih@qti.qualcomm.com

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9243

20 May 03:08
@github-actions github-actions
b9243
17d22a3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9243

hexagon: add MROPE and IMROPE support in HTP rope op (#23317)

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9240

20 May 02:44
@github-actions github-actions
b9240
57cb35c
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9240

common: fix --help for --verbosity (#23278)

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9239

20 May 02:42
@github-actions github-actions
b9239
7256fce
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9239

common: fix --fit verbosity with --verbosity 4 (#23282)

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9235

20 May 03:04
@github-actions github-actions
b9235
d14ce3d
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9235

llama : MTP clean-up (#23269)

  • llama : disable equal splits for recurrent memory with partial rollback

  • spec : re-enable p-min with MTP drafts

  • spec : re-enable ngram spec in combination with RS rollback

  • spec : fix ngram-map-* params

  • spec : fix acceptance logic in combined ngram + draft configs

  • graph : fix reuse for combined token + embd batches

  • spec : log parameters for each speculative implementation

  • add LOG_INF in each constructor with implementation type and parameters
  • extract device string logic into common_speculative_get_devices_str()
  • move 'adding speculative implementation' log from init into constructors

Assisted-by: llama.cpp:local pi

  • spec : extend --spec-default with ngram-map-k4v

Assisted-by: llama.cpp:local pi

  • minor : fix n_embd log

  • args : update draft.n_max == 3 + regen docs

  • spec : relax ngram-mod rejection thold to 0.25 @ 5 low

  • logs : improve

  • docs : update speculative decoding CLI argument documentation

  • Add missing draft model CPU scheduling and tensor override parameters
  • Update --spec-type to include all available types (excluding draft-eagle3 WIP)
  • Fix default values to match implementation (n_max=3, n_min=0, p_min=0.0)
  • Remove deprecated options (spec-draft-ctx-size, spec-draft-replace)
  • Add environment variables for new parameters

Assisted-by: llama.cpp:local pi

  • arg : step-back on adding k4v to the default spec config

  • cont : fix name

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9222

19 May 00:29
@github-actions github-actions
b9222
9a532ae
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9222

hexagon: add support for TRI op (#22822)

  • Hexagon: TRI HVX Kernel addition to ggml hexagon HTP ops and context

  • addressed PR review comments for TRI op

  • hexagon: clang format

  • hex-unary: remove merge conflict markers

  • hex-ggml: remove duplicate op cases (merge conflict)

  • hex-ggml: fix editor config errors

Co-authored-by: Todor Boinovski todorb@qti.qualcomm.com
Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9221

18 May 23:16
@github-actions github-actions
b9221
b734044
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9221

ggml-hexagon: add PAD op HVX kernel (#23078)

  • ggml-hexagon: add PAD op HVX kernel

Implements GGML_OP_PAD on the Hexagon HTP backend using HVX vectorized
kernels. Supports zero-padding and circular padding across all 4 tensor
dimensions.

  • hex-ggml: remove duplicate op cases (merge conflict)

  • hex-pad: fix editorconfig checks and macro alignment

Co-authored-by: Max Krasnyansky maxk@qti.qualcomm.com

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9219

18 May 19:25
@github-actions github-actions
b9219
45b455e
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9219

common : remove hf cache migration (#23266)

Signed-off-by: Adrien Gallouët angt@huggingface.co

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading

b9216

18 May 18:23
@github-actions github-actions
b9216
1ff0fc1
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
b9216

ui: Refactor models store, MCP service, and gate logs behind VITE_DEBUG (#23236)

  • refactor: Scope console logs to DEV + VITE_DEBUG env vars

  • refactor: skip MCP proxy probe when no server requires it

  • refactor: suppress expected disconnect errors during MCP client shutdown

  • refactor: Deduplicate requests

  • refactor: deduplicate model fetching across ROUTER and MODEL modes

  • refactor: Clean up models logic

  • chore: Add .env.example file

  • refactor: replace client-side CORS proxy probe with server status flag

  • refactor: Post-review fixes

  • test: add vitest client setup with API fetch mocks

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Loading