diff --git a/_service b/_service index 3b6781c..cb9bbd3 100644 --- a/_service +++ b/_service @@ -4,7 +4,7 @@ https://github.com/ollama/ollama.git git - v0.1.31 + v0.1.32 @PARENT_TAG@ v(.*) enable @@ -18,4 +18,5 @@ xz + diff --git a/_servicedata b/_servicedata index a2bd40b..43b619e 100644 --- a/_servicedata +++ b/_servicedata @@ -1,4 +1,4 @@ https://github.com/ollama/ollama.git - dc011d16b9ff160c0be3829fc39a43054f0315d0 \ No newline at end of file + fb9580df85c562295d919b6c2632117d3d8cea89 \ No newline at end of file diff --git a/enable-lto.patch b/enable-lto.patch index 393a220..ae8ea1a 100644 --- a/enable-lto.patch +++ b/enable-lto.patch @@ -1,7 +1,7 @@ -diff -rub ollama-0.1.27/llm/generate/gen_linux.sh ollama-0.1.27-patched/llm/generate/gen_linux.sh ---- ollama-0.1.27/llm/generate/gen_linux.sh 2024-02-22 23:41:43.000000000 +0100 -+++ ollama-0.1.27-patched/llm/generate/gen_linux.sh 2024-02-25 03:16:43.566940450 +0100 -@@ -48,7 +48,7 @@ +diff -rub ollama/llm/generate/gen_linux.sh ollama-patched/llm/generate/gen_linux.sh +--- ollama/llm/generate/gen_linux.sh 2024-04-23 04:40:58.246062467 +0200 ++++ ollama-patched/llm/generate/gen_linux.sh 2024-04-23 04:37:36.432294889 +0200 +@@ -51,7 +51,7 @@ export CUDACXX=$(command -v nvcc) fi fi @@ -10,19 +10,19 @@ diff -rub ollama-0.1.27/llm/generate/gen_linux.sh ollama-0.1.27-patched/llm/gene source $(dirname $0)/gen_common.sh init_vars git_module_setup -@@ -59,7 +59,7 @@ - # llama.cpp, and we'll build only 1 CPU variant in that case as the default. +@@ -77,7 +77,7 @@ if [ -n "${OLLAMA_CUSTOM_CPU_DEFS}" ]; then + init_vars echo "OLLAMA_CUSTOM_CPU_DEFS=\"${OLLAMA_CUSTOM_CPU_DEFS}\"" - CMAKE_DEFS="${OLLAMA_CUSTOM_CPU_DEFS} -DCMAKE_POSITION_INDEPENDENT_CODE=on ${CMAKE_DEFS}" + CMAKE_DEFS="${OLLAMA_CUSTOM_CPU_DEFS} -DCMAKE_POSITION_INDEPENDENT_CODE=on -DLLAMA_LTO=on -DCMAKE_BUILD_TYPE=Release ${CMAKE_DEFS}" - BUILD_DIR="${LLAMACPP_DIR}/build/linux/${ARCH}/cpu" + BUILD_DIR="../build/linux/${ARCH}/cpu" echo "Building custom CPU" build -@@ -75,7 +75,7 @@ +@@ -93,7 +93,7 @@ # -DLLAMA_AVX512_VBMI -- 2018 Intel Cannon Lake # -DLLAMA_AVX512_VNNI -- 2021 Intel Alder Lake - + - COMMON_CPU_DEFS="-DCMAKE_POSITION_INDEPENDENT_CODE=on -DLLAMA_NATIVE=off" + COMMON_CPU_DEFS="-DCMAKE_POSITION_INDEPENDENT_CODE=on -DLLAMA_LTO=on -DCMAKE_BUILD_TYPE=Release -DLLAMA_NATIVE=off" if [ -z "${OLLAMA_CPU_TARGET}" -o "${OLLAMA_CPU_TARGET}" = "cpu" ]; then diff --git a/ollama-0.1.31.tar.gz b/ollama-0.1.31.tar.gz deleted file mode 100644 index 9f437dd..0000000 --- a/ollama-0.1.31.tar.gz +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e55ac3bbb965f56c6920b793f254e814f4bf5fea77c81e8d8d867e850b15394 -size 80992137 diff --git a/ollama-0.1.32.tar.gz b/ollama-0.1.32.tar.gz new file mode 100644 index 0000000..1451f75 --- /dev/null +++ b/ollama-0.1.32.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b648bcafa46320c876a83a817f4fc4ed6c8a8acc961d62f4adb017fa7ad053 +size 70152034 diff --git a/ollama.changes b/ollama.changes index 9a54f83..6085995 100644 --- a/ollama.changes +++ b/ollama.changes @@ -1,3 +1,91 @@ +------------------------------------------------------------------- +Tue Apr 23 02:26:34 UTC 2024 - rrahl0@disroot.org + +- Update to version 0.1.32: + * scale graph based on gpu count + * Support unicode characters in model path (#3681) + * darwin: no partial offloading if required memory greater than system + * update llama.cpp submodule to `7593639` (#3665) + * fix padding in decode + * Revert "cmd: provide feedback if OLLAMA_MODELS is set on non-serve command (#3470)" (#3662) + * Added Solar example at README.md (#3610) + * Update langchainjs.md (#2030) + * Added MindsDB information (#3595) + * examples: add more Go examples using the API (#3599) + * Update modelfile.md + * Add llama2 / torch models for `ollama create` (#3607) + * Terminate subprocess if receiving `SIGINT` or `SIGTERM` signals while model is loading (#3653) + * app: gracefully shut down `ollama serve` on windows (#3641) + * types/model: add path helpers (#3619) + * update llama.cpp submodule to `4bd0f93` (#3627) + * types/model: make ParseName variants less confusing (#3617) + * types/model: remove (*Digest).Scan and Digest.Value (#3605) + * Fix rocm deps with new subprocess paths + * mixtral mem + * Revert "types/model: remove (*Digest).Scan and Digest.Value (#3589)" + * types/model: remove (*Digest).Scan and Digest.Value (#3589) + * types/model: remove DisplayLong (#3587) + * types/model: remove MarshalText/UnmarshalText from Digest (#3586) + * types/model: init with Name and Digest types (#3541) + * server: provide helpful workaround hint when stalling on pull (#3584) + * partial offloading + * refactor tensor query + * api: start adding documentation to package api (#2878) + * examples: start adding Go examples using api/ (#2879) + * Handle very slow model loads + * fix: rope + * Revert "build.go: introduce a friendlier way to build Ollama (#3548)" (#3564) + * build.go: introduce a friendlier way to build Ollama (#3548) + * update llama.cpp submodule to `1b67731` (#3561) + * ci: use go-version-file + * Correct directory reference in macapp/README (#3555) + * cgo quantize + * no blob create if already exists + * update generate scripts with new `LLAMA_CUDA` variable, set `HIP_PLATFORM` to avoid compiler errors (#3528) + * Docs: Remove wrong parameter for Chat Completion (#3515) + * no rope parameters + * add command-r graph estimate + * Fail fast if mingw missing on windows + * use an older version of the mac os sdk in release (#3484) + * Add test case for context exhaustion + * CI missing archive + * fix dll compress in windows building + * CI subprocess path fix + * Fix CI release glitches + * update graph size estimate + * Fix macOS builds on older SDKs (#3467) + * cmd: provide feedback if OLLAMA_MODELS is set on non-serve command (#3470) + * feat: add OLLAMA_DEBUG in ollama server help message (#3461) + * Revert options as a ref in the server + * default head_kv to 1 + * fix metal gpu + * Bump to b2581 + * Refined min memory from testing + * Release gpu discovery library after use + * Safeguard for noexec + * Detect too-old cuda driver + * Integration test improvements + * Apply 01-cache.diff + * Switch back to subprocessing for llama.cpp + * Simplify model conversion (#3422) + * fix generate output + * update memory calcualtions + * refactor model parsing + * Add chromem-go to community integrations (#3437) + * Update README.md (#3436) + * Community Integration: CRAG Ollama Chat (#3423) + * Update README.md (#3378) + * Community Integration: ChatOllama (#3400) + * Update 90_bug_report.yml + * Add gemma safetensors conversion (#3250) + * CI automation for tagging latest images + * Bump ROCm to 6.0.2 patch release + * CI windows gpu builds + * Update troubleshooting link + * fix: trim quotes on OLLAMA_ORIGINS + +- add set_version to automatically switch over to the newer version + ------------------------------------------------------------------- Tue Apr 16 10:52:25 UTC 2024 - bwiedemann@suse.com diff --git a/ollama.spec b/ollama.spec index 0fbbc20..a31ce21 100644 --- a/ollama.spec +++ b/ollama.spec @@ -17,7 +17,7 @@ Name: ollama -Version: 0.1.31 +Version: 0.1.32 Release: 0 Summary: Tool for running AI models on-premise License: MIT diff --git a/vendor.tar.xz b/vendor.tar.xz index e3679a7..851ca2e 100644 --- a/vendor.tar.xz +++ b/vendor.tar.xz @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:924b704ac695115d54330397b6d02d737de88d5f67fa760fd1065521357193fd -size 3656224 +oid sha256:26f50ef1d227317f77b0a68eb9672f407c3bdd15ffcd3bf6011afdf9b7d3b5ff +size 3669792