From a995c210baa6670c3eaf8b83031a2ad46c0c5caf Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Wed, 14 Oct 2026 04:10:53 -0700 Subject: [PATCH] pr-set: repin ggml-org#24423, ggml-org#25731, unslothai#158, unslothai#149 onto b11609, drop unslothai#152 (upstream ggml-org#30405) --- scripts/unsloth/feature-checks.json | 3 +-- scripts/unsloth/pr-set.json | 9 ++++----- 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/scripts/unsloth/feature-checks.json b/scripts/unsloth/feature-checks.json index 7c4e387b98af..e6baf9faf1ca 100644 --- a/scripts/unsloth/feature-checks.json +++ b/scripts/unsloth/feature-checks.json @@ -95,8 +95,7 @@ }, "unchecked": { "unslothai#95": "sampling penalties indexed by token id; behaviour is covered by test-sampling, and there is no feature surface of its own to probe", - "unslothai#149": "GGML_CUDA_ENABLE_UNIFIED_MEMORY=0 env parsing; needs a CUDA or HIP host, and no runner in the pipeline has one", - "unslothai#152": "per-run mmap of a context's tensors; a memory-layout change with no observable output difference", + "unslothai#149": "once-per-process HIP warning when GGML_CUDA_ENABLE_UNIFIED_MEMORY is on (=0 parsing is upstream since ggml-org#30327); needs a HIP host, and no runner in the pipeline has one", "unslothai#157": "cudaMemcpyDefault in the ggml_cuda_cpy 2D fast path; needs a CUDA host", "unslothai#158": "ROCm_Host compute buffer type on HIP integrated GPUs; needs a ROCm host", "unslothai#241": "CUDA graph cache keyed by shape with no count cap (tensor split keeps replaying its 2 * n_layers + 1 graphs per device), macOS row prefetch and the F16 glm5-next indexer cache under a quantized -ctk (the NextN draft graph is upstream since ggml-org#29928); the first needs a CUDA host (multi-GPU for the cap), the second has no observable output difference, the last needs a real GLM-5-Next model", diff --git a/scripts/unsloth/pr-set.json b/scripts/unsloth/pr-set.json index 2eebe6a5db27..717b50227f83 100644 --- a/scripts/unsloth/pr-set.json +++ b/scripts/unsloth/pr-set.json @@ -18,15 +18,14 @@ "tag + pins), so keep its pin listed until the change lands upstream." ], "prs": [ - "https://github.com/ggml-org/llama.cpp/pull/24423/commits/c9b81bef4c8c6ed3dd9549d990df979b44668f59", - "https://github.com/ggml-org/llama.cpp/pull/25731/commits/2182bee3ad50cc248807f5785f7fdc54d1c16bc5", + "https://github.com/ggml-org/llama.cpp/pull/24423/commits/6a7388aac74ab896d9d4f0fb187ddac4847c02f0", + "https://github.com/ggml-org/llama.cpp/pull/25731/commits/607b193a546bf7ebd17cca1c3e355c622fcef605", "https://github.com/unslothai/llama.cpp/pull/70/commits/883f2c9ba78f3847148454adf025da29385fff3e", "https://github.com/unslothai/llama.cpp/pull/61/commits/02a015c22ad0f9a6a2b1d4361900b45aa212f936", "https://github.com/unslothai/llama.cpp/pull/95/commits/3db8cb5b2e9bf291057b9f19960e8601a162da81", - "https://github.com/unslothai/llama.cpp/pull/158/commits/abfc45b9cb21eae4848cb82196e659f42c9a8341", + "https://github.com/unslothai/llama.cpp/pull/158/commits/fb9b9462041ad58cde9a274e7984c3c6fb01b279", "https://github.com/unslothai/llama.cpp/pull/157/commits/6c6da89266ba7839d825c9997782af4f4d26b81b", - "https://github.com/unslothai/llama.cpp/pull/149/commits/b65a2dce12c14a489e19a059cb6ee59112f1b733", - "https://github.com/unslothai/llama.cpp/pull/152/commits/b2b5ed9ff86427a530b762a45d3fdbd453bcd4e8", + "https://github.com/unslothai/llama.cpp/pull/149/commits/30d39d74fd9cad3224c30bdda3a9def6c9aa6719", "https://github.com/unslothai/llama.cpp/pull/176/commits/e2519ebc09468b477847a7529834a8da998ed2da", "https://github.com/unslothai/llama.cpp/pull/239/commits/bec216444552a20bc39bf2156fa5396154970608", "https://github.com/unslothai/llama.cpp/pull/240/commits/d9dd1810da0075ff0000a352055ab246b2738d5e",