From 664babefa4013d86953e430761b183f8eea5482a Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Mon, 5 Oct 2026 06:34:00 -0700 Subject: [PATCH] unsloth: drop the pins upstream superseded and repin the conflict-fixed heads Drop ggml-org#27754, #144 and #137: upstream merged GLM-5-Next (#27773), Qwen4Exp MTP (#29761) and row prefetch (#29599), and the old pins no longer merge. Old-GGUF loading moves to #239, shared MTP heads to #240, and what the dropped pins had beyond upstream to #241. Repin ggml-org#24423, ggml-org#25731, #61 and #176 to their conflict-fixed heads. --- scripts/unsloth/feature-checks.json | 10 +++++----- scripts/unsloth/pr-set.json | 14 +++++++------- 2 files changed, 12 insertions(+), 12 deletions(-) diff --git a/scripts/unsloth/feature-checks.json b/scripts/unsloth/feature-checks.json index 93fe8d3c18f5..c5b9ff53e8d1 100644 --- a/scripts/unsloth/feature-checks.json +++ b/scripts/unsloth/feature-checks.json @@ -52,9 +52,9 @@ ] }, "glm5next": { - "owner": "ggml-org#27754", + "owner": "unslothai#239", "checks": [ - { "kind": "arch", "arch": "glm5next" }, + { "kind": "arch", "arch": "glm5-next" }, { "kind": "backend-op", "op": "LIGHTNING_INDEXER" } ] }, @@ -80,7 +80,7 @@ ] }, "qwen4exp-mtp": { - "owner": "unslothai#144", + "owner": "unslothai#240", "checks": [ { "kind": "arch", "arch": "qwen4exp" }, { "kind": "backend-op", "op": "TOPK_QSA" } @@ -95,10 +95,10 @@ }, "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#137": "batched readahead for lazily read gather tables; a throughput change with no observable output difference", "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#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#158": "ROCm_Host compute buffer type on HIP integrated GPUs; needs a ROCm host", + "unslothai#241": "CUDA graph cache key, macOS row prefetch, F16 glm5-next indexer cache under a quantized -ctk and the glm5-next NextN draft graph; the first needs a CUDA host, the second has no observable output difference, the last two need a real GLM-5-Next NextN head with --spec-type draft-mtp" } } diff --git a/scripts/unsloth/pr-set.json b/scripts/unsloth/pr-set.json index 86c807badf0c..3063216055ec 100644 --- a/scripts/unsloth/pr-set.json +++ b/scripts/unsloth/pr-set.json @@ -18,18 +18,18 @@ "tag + pins), so keep its pin listed until the change lands upstream." ], "prs": [ - "https://github.com/ggml-org/llama.cpp/pull/24423/commits/3dac51dc80b1400929266453c6ced6748ccf6862", - "https://github.com/ggml-org/llama.cpp/pull/25731/commits/3870aa48bbed3d5b1ee7cded0de688baa42f2470", + "https://github.com/ggml-org/llama.cpp/pull/24423/commits/643189144c98fba431e8d2da169210b7b6d5d930", + "https://github.com/ggml-org/llama.cpp/pull/25731/commits/efd2b13f80c68df745f0134a2a0f56a434a2d33d", "https://github.com/unslothai/llama.cpp/pull/70/commits/883f2c9ba78f3847148454adf025da29385fff3e", - "https://github.com/unslothai/llama.cpp/pull/61/commits/46cbf0e95786fe8f5b7c0e86d57aaf8f8eceea7f", + "https://github.com/unslothai/llama.cpp/pull/61/commits/ef45f212c90d5769e0dd8d482f99fd66760312e7", "https://github.com/unslothai/llama.cpp/pull/95/commits/3db8cb5b2e9bf291057b9f19960e8601a162da81", - "https://github.com/ggml-org/llama.cpp/pull/27754/commits/86ebfef2c6a0f3359a2a07d2c215d61b0fa885c9", - "https://github.com/unslothai/llama.cpp/pull/137/commits/4e1865e34ec5f6ca39403215c89129c13731be70", "https://github.com/unslothai/llama.cpp/pull/158/commits/abfc45b9cb21eae4848cb82196e659f42c9a8341", "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/144/commits/ca1426903fabe9af26cd10c42034cb4bbd2e0e11", "https://github.com/unslothai/llama.cpp/pull/152/commits/b2b5ed9ff86427a530b762a45d3fdbd453bcd4e8", - "https://github.com/unslothai/llama.cpp/pull/176/commits/09ce1a4d2939844e211f7b4d30a296f4c1aed9a8" + "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/36175a8325e24303704cfbab1b7d8a0bd30500a5", + "https://github.com/unslothai/llama.cpp/pull/241/commits/b96a713a48313a32c92fd6f77b367ea9d803417b" ] }