Skip to content

Releases: ggml-org/llama.cpp

b9739

20 Jun 15:29
8452824

Choose a tag to compare

b9738

20 Jun 14:06
e27f308

Choose a tag to compare

server: avoid forwarding auth headers in CORS proxy (#24373)

  • server: avoid forwarding auth headers in CORS proxy

  • format

  • fix test

  • fix e2e test


Co-authored-by: Xuan Son Nguyen son@huggingface.co

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9736

20 Jun 11:59
796f41b

Choose a tag to compare

model : glm-dsa load DSA indexer tensors as optional (#24770)

GLM-5.2 ships the DSA "lightning indexer" on only a subset of layers (the
"full" layers; others omit it), but the GLM_DSA loader created the five
indexer tensors on every layer as required, so loading any GLM-5.2 GGUF
failed with e.g. missing tensor 'blk.3.indexer.k_norm.weight'.

GLM_DSA's graph is llama_model_deepseek2::graph (plain MLA) and does not use
the indexer tensors (indexer runtime not yet implemented), so they are
loaded-but-unused. Marking them TENSOR_NOT_REQUIRED lets layers without an
indexer load as nullptr and the model runs as full MLA attention.

DeepSeek-V3.2 (uniform indexer on all layers) is unaffected.

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9735

20 Jun 11:33
37a77fb

Choose a tag to compare

ggml : optimize AMX (#24806)

Flatten the partition over n_batch * M so every thread participates in
the quantization

| CPU                             | Model                         | Test   |   t/s OLD |   t/s NEW |   Speedup |
|:--------------------------------|:------------------------------|:-------|----------:|----------:|----------:|
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B IQ4_NL - 4.5 bpw  | pp512  |    730.71 |    779.86 |      1.07 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B IQ4_NL - 4.5 bpw  | tg128  |     87.88 |     86.79 |      0.99 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B IQ4_XS - 4.25 bpw | pp512  |    725.09 |   1023.31 |      1.41 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B IQ4_XS - 4.25 bpw | tg128  |     83.64 |     83.62 |      1.00 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_0              | pp512  |    820.51 |    924.05 |      1.13 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_0              | tg128  |     90.59 |     92.46 |      1.02 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_1              | pp512  |    776.88 |    872.79 |      1.12 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_1              | tg128  |     89.39 |     90.94 |      1.02 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_K_M            | pp512  |    719.28 |   1009.27 |      1.40 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_K_M            | tg128  |     80.62 |     80.86 |      1.00 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_K_S            | pp512  |    732.29 |   1077.29 |      1.47 |
| Intel(R) Xeon(R) Platinum 8488C | qwen35 0.8B Q4_K_S            | tg128  |     86.42 |     83.53 |      0.97 |

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

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9733

20 Jun 00:16
f449e05

Choose a tag to compare

b9732

19 Jun 23:44
2b686a9

Choose a tag to compare

server: refactor child --> router communication (#24821)

  • server: refactor child --> router communication

  • fix wakeup case

  • add docs

  • improve update_status()

  • nits

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9731

19 Jun 21:54
4b48a53

Choose a tag to compare

server : optimize get_token_probabilities (#24796)

Use std::partial_sort to order only the requested top-n tokens instead
of the full vocabulary

logprobs sort: vocab=128000 n_top=0 iters=100
full    sort:   8555.6 us/op
partial sort:    704.3 us/op

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

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9730

19 Jun 21:18
e475fa2

Choose a tag to compare

mtmd, arg: fix utf8 handling on windows (#24779)

  • mtmd, arg: fix utf8 handling on windows

  • also fix ggml_fopen

  • fix build fail

  • also fix CLI

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

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

UI:

b9729

19 Jun 20:47
175147e

Choose a tag to compare

b9728

19 Jun 16:19
fabde3b

Choose a tag to compare