Loading
Loading page content.Loading
Loading page content.Open systems / 03
Find new AI tools and meaningful releases with source links, adoption context, and practical tradeoffs.
## [3.9.0](https://github.com/openai/openai-python/compare/v3.8.0...v3.9.0) (2026-09-05) ### Features * **api:** Add prompt cache diagnostics ([#3800](https://github.com/openai/openai-python/issues/3800)) ([8326784](https://github.com/openai/openai-python/commit/83267847a0219ea8…
github.com1 month agoView details
langchain-ai/langchain langchain-openai==1.6.1
Changes since langchain-openai==1.6.0 fix(openai): bump `max_completion_tokens` in cache breakpoint integration test (#40284) release(openai): 1.6.1 (#40268) chore(model-profiles): refresh model profile data (#40217) fix(openai): support Azure AD auth with OpenAI 3.8 (#40190) fe…
github.com1 month agoView details
<details open> model : support Kimi-K3 recurrent-state rollback (#28466) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45866131> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/lla…
github.com1 month agoView details
<details open> hexagon: add RELU and LEAKY_RELU ops (#28585) * hexagon: add RELU op * hexagon: add LEAKY_RELU op too </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45844223> **macOS/iOS:** - [macOS Apple Sili…
github.com1 month agoView details
<details open> tests : initialize the L2_NORM batch array (#28553) * tests: bind the L2_NORM batch count to a local GCC cannot prove the loop fills norms up to the index read after it while the bound is a class member, so it reports a maybe uninitialized use. Reading the count o…
github.com1 month agoView details
<details open> caps : recheck typed content if template checks for string (#28511) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45690927> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/gg…
github.com1 month agoView details
<details open> ggml-cuda: fix divergent barrier in f16 flash attention (#27870) * ggml-cuda: fix divergent barrier in f16 flash attention * ggml-cuda: avoid duplicate metadata pointer setup </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggm…
github.com1 month agoView details
<details open> ggml: allow backend inputs to not create another split (#28387) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45674860> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-o…
github.com1 month agoView details
<details open> metal : fix memory leak in early return (#28399) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45438612> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/re…
github.com1 month agoView details
<details open> sycl : fix test-backend-ops CI break && restore Kronecker product FWHT support (#28016) (#28254) * Reapply "sycl : add Kronecker product FWHT support for sizes 384, 640, 768, 12…" (#28184) This reverts commit c845263f8b7d60113e213a3bd2d5cc6472ccf204. * tests : fix…
github.com1 month agoView details
<details open> sycl: attribute device allocations by site (GGML_SYCL_MEMTRACE) (#27631) define two new environment variables to better understand how much memory is being allocated, and when. This has been invaluable in inproving the --fit algorithm, and is likely to be useful w…
github.com1 month agoView details
<details open> vulkan : only request VK_KHR_shader_bfloat16 extension if supported (#28155) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/44637403> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://gith…
github.com2 months agoView details
<details open> opencl: fix out‐of‐bound reads in the Adreno image kernels (#27632) * opencl: clamp the q4_K decode GEMV's fetch row on a padded x-grid * opencl: enforce the tiling contract of the image KQ/KQV GEMMs * opencl: decide the image KQ/KQV split at the dispatch, not fro…
github.com2 months agoView details
<details open> hexagon: add missing FARF logs for cpy/get_rows/set_rows/gdn ops (#28217) * hexagon: fix bug ne[2] printed in proc_op_req prep-src log * hexagon: add shape/VTCM farf logs to cpy, get/set rows, gdn </details> **Website:** - <https://llama.app> **Attestations:** - <…
github.com2 months agoView details
langchain-ai/langchain langchain==1.4.0a4
Initial release release(langchain): 1.4.0a4 test(langchain): cover mixed-era ClientGroup and group elicitation Update libs/langchain_v1/langchain/mcp/adapter.py fix(langchain): drive MCP elicitation via member session for fastmcp 4.0.1 fix(sdk): use latest fastmcp and rm reentra…
github.com2 months agoView details
## [3.7.0](https://github.com/openai/openai-python/compare/v3.6.0...v3.7.0) (2026-09-02) ### Features * **api:** update usage APIs and documentation ([#3779](https://github.com/openai/openai-python/issues/3779)) ([6f0da16](https://github.com/openai/openai-python/commit/6f0da1657…
github.com2 months agoView details
anthropics/anthropic-sdk-python v1.4.0
## 1.4.0 (2026-09-04) Full Changelog: [v1.3.0...v1.4.0](https://github.com/anthropics/anthropic-sdk-python/compare/v1.3.0...v1.4.0) ### Features * **api:** add Claude Tag category and user breakdowns to usage reports ([9fce1e4](https://github.com/anthropics/anthropic-sdk-python/…
github.com1 month agoView details
langchain-ai/langchain langchain-core==1.6.2
Changes since langchain-core==1.6.1 release(core): 1.6.2 (#40209) feat(openai): support async tools (#40208) chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/core (#40150) chore(deps): bump tornado from 6.5.7 to 6.5.8 in /libs/core (#40113) fix(core): avoid mutation in goo…
github.com1 month agoView details
<details open> metal : add remaining fa-vec tunings for M3 (#28396) * addition of m3 in fa_vec_tuned_table * adding q4_0,q4_1,q5_0,q5_1 in ggml-metal-tuning * Fix formatting in ggml-metal-tuning.cpp </details> **Website:** - <https://llama.app> **Attestations:** - <https://githu…
github.com1 month agoView details
## Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with major sparse flash attention and RDMA work. ### API changes - Added `llama_l…
github.com1 month agoView details
<details open> opencl: extend the elementwise and data‐movement op coverage (#27633) * opencl: add extended elementwise unary ops (sgn, step, elu, hardswish, hardsigmoid, floor, ceil, round, trunc) Adds nine GGML_UNARY_OP_* elementwise ops that were falling back to CPU on the Op…
github.com1 month agoView details
anthropics/anthropic-sdk-python v1.3.0
## 1.3.0 (2026-09-01) Full Changelog: [v1.2.0...v1.3.0](https://github.com/anthropics/anthropic-sdk-python/compare/v1.2.0...v1.3.0) ### Features * **api:** beta user profiles: add external_user_onboarded_at, remove relationship in favor of access_type ([74080c3](https://github.c…
github.com2 months agoView details
langchain-ai/langchain langchain==1.4.0a3
Third alpha of the `1.4.0` line. This release focuses on the new `langchain.mcp` namespace for adapting MCP servers into LangChain tools. ## `langchain.mcp` highlights - **`MCPAdapter`** adapts any target `fastmcp.Client` accepts — a URL, a local script, an in-process server, an…
github.com2 months agoView details
<details open> ggml-cpu(s390x) : fix q5_1 uninitialized v_acc (#28332) Signed-off-by: Aaron Teo <aaron.teo1@ibm.com> </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45199911> **macOS/iOS:** - [macOS Apple Sili…
github.com1 month agoView details
<details open> sycl: reduce redundant work in Q4_K multi-column MMVQ (#27062) * sycl: Q4_K Weight unpack optimization and reuse between destination Columns * sycl: Q4_K small N (N=2..4) + two output rows by subgroup reuse of activation between two rows. * sycl: gate Q4_K two-row…
github.com2 months agoView details
<details open> vendor : update subprocess.h (#27409) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42402532> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/down…
github.com2 months agoView details
<details open> sycl: fuse mul_mat(gate) + mul_mat(up) + GLU for q4_K dense FFN (#26779) Measured on Arc Pro B70 (Battlemage, Level Zero), llama-bench -r 20, two interleaved rounds, tg128: qwen2.5-3B-Instruct Q4_K_M 154.18 -> 158.53 t/s +2.8% gemma-2-2b-it Q4_K_M 162.45 -> 165.62…
github.com2 months agoView details
<details open> common : fix draft-mtp with embeddings (#26352, #27299) (#27400) * common: fix draft-mtp with embeddings (#26352) * --whitespace --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> </details> **Website:** - <https://llama.app> **Attestati…
github.com2 months agoView details
<details open> cuda : add POOL_1D support (#27573) * cuda : add POOL_1D support * fix: add missing trailing newline for editorconfig compliance </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42401257> **macOS…
github.com2 months agoView details
<details open> model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444) * hparams: add per-layer n_ff_exp/n_expert_used arrays with scalar-or-array loading G1/G2 infrastructure for variable-per-layer expert FFN size and top-k routing (required for Puzzle-75…
github.com2 months agoView details
<details open> sycl : add Q2_K reordered MMVQ and ESIMD kernels (again) (#27490) * Revert "Revert "sycl : add Q2_K reordered MMVQ and ESIMD kernels (#26336)" (#…" This reverts commit 7a0e42fd01fb0acda644e4f04b1f1acbbb9e23ba. * add gate params </details> **Website:** - <https://l…
github.com2 months agoView details
<details open> memory : copy Hadamard matrix to k_rot tensor only if it has buffer assigned to prevent crashes during context shift of unquantized K cache (#27967) Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: AesSedai <7980540+AesSedai@users.noreply.gi…
github.com2 months agoView details
<details open> ggml-hip : remove -funsafe-math-optimizations (#26696) It enables -fassociative-math, which reassociates FP reductions and can flip greedy argmax on RDNA3.5 (e.g. MTP speculative decode diverging from the non-speculative baseline). Drop it so HIP builds are IEEE-c…
github.com2 months agoView details
<details open> ggml: force single thread on wasi (#25686) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10426/llama-b10426-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64…
github.com2 months agoView details
<details open> llama : check LoRA tensor data is within file bounds (#27056) * llama : check LoRA tensor data is within file bounds * Update src/llama-adapter.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigb…
github.com2 months agoView details
<details open> tests : run test-save-load-state across all architectures (#27755) * tests : run test-save-load-state across all architectures test-save-load-state previously only ran in ctest against a single downloaded model (tinyllamas/stories15M), i.e. only the llama arch. Ad…
github.com2 months agoView details
<details open> grammar : parse \- in char classes as literal hyphen (#27591) * grammar : accept "\-" escape in character classes gbnf_escape_char_class() escapes '-' as "\-" but parse_char() rejected that escape, so generated tool-call grammars failed to parse. Assisted-by: Clau…
github.com2 months agoView details
<details open> ggml: add ggml_rope_set_offset (+ metal support) (#27120) * add params * cpu kernel * metal kernel * add test backend ops * gate other backends * ggml: (cuda) support ggml_rope_set_offset (#27121) * rm cuda supports_op guard, fix webgpu clang-format * ggml: suppor…
github.com2 months agoView details
<details open> sycl: fuse the gated-delta-net state writeback cpy (#26643) Port of https://github.com/ggml-org/llama.cpp/pull/23940. Arc Pro B70, Qwen 3.6 27B Q4_K - Medium (48 of its 64 blocks run gated_delta_net), -ngl 99 -fa 1 -ctk f16 -ctv f16 -b 2048 -ub 2048, interleaved A…
github.com2 months agoView details
<details open> sycl : mark tq2_0 as not supported (#27660) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42777546> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/release…
github.com2 months agoView details
<details open> sycl: fix thread/block count in quantized cpy kernel launches (#27160) Adjusts the thread/block count to be proportional to the size of the quant, reducing under/over subscription. Largest perf improvement is the q4_0 -> f32 path, with, on a Arc 70, throughput goe…
github.com2 months agoView details
<details open> ggml-meta: propagate buffer usage and call init on the new tensors (#27586) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43044002> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://githu…
github.com2 months agoView details
<details open> ggml : fix arm builds, unused var (#26991) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10400/llama-b10400-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64…
github.com2 months agoView details
<details open> [SYCL] support OP OPT_STEP_ADAMW, OPT_STEP_SGD (#25268) * fix conflict * fix conflict of ops.md * fix conflict of ops.md * update the ops.md --------- Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com> </details> **Website:** - <https://llama.app> **macOS/i…
github.com2 months agoView details
<details open> vulkan: top_k radix select for k >= 1024 for Qwen 3.8 Flash Next (#28032) * vulkan: add top-k radix sort shader for k >= 1024 * add Qwen 3.8 Flash Next top-k tests * add top-k qsa fusion * clean up code </details> **Website:** - <https://llama.app> **Attestations:…
github.com2 months agoView details
<details open> qwen4exp: support recurrent state rollback (#28123) MTP speculative decoding needs the target state to move back by the number of rejected draft tokens. Without rollback support the context is classified as SEQ_RM_TYPE_FULL and the server serializes the whole recu…
github.com2 months agoView details
<details open> src : add n_expert_used_max function (#28323) * src : add n_expert_used_max function With Commit c61b98b875eaa5e654a3f5c73b34c310d2c6ab4c ("model: add NVIDIA Nemotron-3-Puzzle-75B-A9B (NemotronHPuzzle) support (#25444)") it is now possible for each layer to have a…
github.com1 month agoView details
<details open> model : add support for MiniMaxText01ForCausalLM and MiniMaxM1ForCausalLM (#27018) * llama : support for MiniMax-Text-01 model * chore : renames to match the other MiniMax models * model : add logits mask as MiniMax-Text-01 embeddings tensor has zero-valued embedd…
github.com2 months agoView details
<details open> models : support nanbeige4.2-3B (#27730) Co-authored-by: admin <lizongqiang@kanzhun.com> </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43308396> **macOS/iOS:** - [macOS Apple Silicon (arm64)](…
github.com2 months agoView details
<details open> qwen4exp: sum the indexer heads by slices (#28023) * qwen4exp: sum the indexer heads by slices The head reduction went through a transpose and a sum_rows over ne[1], which left sum_rows with ne0 = 4, one block per row for a four element reduction, and the transpos…
github.com2 months agoView details
Newsletter
Receive source-checked analysis of models, agents, evaluation, retrieval, and production reliability. Sent only when there is useful work to share.