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.
<details open> mtmd: support pocket-tts (#26871) * adapt the api * text model ok * working impl, need verify and clean up * mtmd: build the pocket-tts transposed convolutions as GEMM + col2im ggml_conv_transpose_1d has no grouped mode, so the depthwise upsample was built as one…
github.com2 months agoView details
<details open> hexagon: fix CPY fence bug (#28033) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/44046740> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/downlo…
github.com2 months agoView details
<details open> sycl: fuse rms_norm+mul+add and add+add residual chains (#27610) Fuse RMS_NORM+MUL+ADD and ADD+ADD under GGML_SYCL_ENABLE_FUSION. ADD+ADD uses the same binbcast indexing and type matrix as standalone add() (f32, f16, f16/f32, i32, i16, bf16, including broadcast an…
github.com1 month agoView details
<details open> metal : add remaining Q4_1/Q5_0/Q5_1 fa-vec tunings for M2 (#28017) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/44044108> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/gg…
github.com2 months agoView details
<details open> mtmd, common: various fixes (#27071) * apply fixes * cont * revert gguf fix </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10436/llama-b10436-bin-macos-arm64.tar…
github.com2 months agoView details
<details open> ggml: allow passing alloc dependencies in graph_optimize (#27301) * ggml: allow passing alloc dependencies in graph_optimize * add alloc dep tests * add TODO about using flat array </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.c…
github.com2 months agoView details
modelcontextprotocol/servers 2026.7.10
# Release : v2026.7.10 ## Updated packages - @modelcontextprotocol/server-filesystem@2026.7.10 - mcp-server-time@2026.7.10 - mcp-server-fetch@2026.7.10 - mcp-server-git@2026.7.10
github.com3 months agoView details
<details open> metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450) The Tensor API mat-mat path of kernel_mul_mm (GGML_METAL_HAS_TENSOR) fed a static K=32 tile to the matmul2d op on every iteration. On the last, partial K tile (ne00 % 32 != 0)…
github.com2 months agoView details
<details open> mtmd: add --mmproj-device argument (#23255) * feat: add --mmproj-device arg & backwards compatible MTMD_BACKEND_DEVICE env var * feat: load mmproj device backend immediately, add -mmdev shortflag * fix: its a pointer now get the name * clean up * gen docs * nits -…
github.com2 months agoView details
<details open> mtmd: add mtmd_bitmap_set_mergeable (#27348) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10507/llama-b10507-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm…
github.com2 months agoView details
<details open> vulkan: FA MMQ should use fp32 for Q quantization calculations (#27413) Codex found that qd could be a denorm and 1/qd would overflow. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42034841> *…
github.com2 months agoView details
<details open> metal : dequantize q8_0 using packed types (#27370) </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b10506/llama-b10506-bin-macos-arm64.tar.gz) - macOS Apple Silic…
github.com2 months agoView details
langchain-ai/langchain langchain==1.3.17
Changes since langchain==1.3.16 release(langchain): 1.3.17 (#39893) fix(langchain): frame custom HITL rejection reasons (#39773) chore(deps): bump minor and patch dependencies (#39869)
github.com2 months agoView details
langchain-ai/langchain langchain-anthropic==1.5.6
Changes since langchain-anthropic==1.5.5 release(anthropic): 1.5.6 (#39622) fix(anthropic): normalize `tool_search_tool_result` blocks (#39621) fix(anthropic): correct model profile data for Fable 5, Sonnet 5, Opus 4.1 (#39604)
github.com2 months agoView details
<details open> mtmd: fix idefics3 preproc (#28273) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/44875193> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/downlo…
github.com2 months agoView details
<details open> hexagon: support for multi-NPU devices (IQ9, IQ10) and fully asynchronous backend (#26501) * hexagon: use non-host bufs by default and make the backend fully async * hex-hb: remove optional hostbuf support and fix async copy * hex-unary: relax supported unary chec…
github.com2 months agoView details
## [3.0.0](https://github.com/openai/openai-python/compare/v2.54.0...v3.0.0) (2026-08-12) ### ⚠ BREAKING CHANGES * **api:** HTTPX2 is now the default HTTP client, and `httpx` is no longer installed automatically. Applications using custom HTTPX clients, transports, or configurat…
github.com2 months agoView details
langchain-ai/langchain langchain-openai==1.5.2a1
Initial release release(openai): 1.5.2a1 (#39709) feat(openai): extract gateway metadata from response headers when available (#39706) chore(openai): update snapshots (#39657) fix(openai): support o-series models in `get_num_tokens_from_messages` (#38710) release(openai): 1.5.1…
github.com2 months agoView details
# vLLM v0.26.0 Release Notes ## Highlights This release features 411 commits from 212 contributors (61 new)! * **New Inkling model family** with a full support stack: base modeling (#48799), piecewise CUDA graph support (#48822), Hopper FA4 relative attention (#48858), MTP=1 spe…
github.com3 months agoView details
## [3.5.0](https://github.com/openai/openai-python/compare/v3.4.0...v3.5.0) (2026-08-27) ### Features * **api:** make function call output call IDs optional ([#3738](https://github.com/openai/openai-python/issues/3738)) ([c74501d](https://github.com/openai/openai-python/commit/c…
github.com2 months agoView details
<details open> model: add DSpark support for Nemotron3.5 (#27804) * model: add DSpark support for Nemotron3.5 * Update src/models/dflash.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co> --------- Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingf…
github.com2 months agoView details
<details open> metal : add fa-vec tunings for M2 (#27940) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43902029> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases…
github.com2 months agoView details
## [3.1.0](https://github.com/openai/openai-python/compare/v3.0.0...v3.1.0) (2026-08-14) ### Features * **api:** add WebSocket stream IDs ([#3612](https://github.com/openai/openai-python/issues/3612)) ([d9029e3](https://github.com/openai/openai-python/commit/d9029e3ada3c008b4631…
github.com2 months agoView details
<details open> common: json.h: fix clang lto (#27575) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42368523> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/dow…
github.com2 months agoView details
modelcontextprotocol/servers 2026.7.4
# Release : v2026.7.4 ## Updated packages - @modelcontextprotocol/server-everything@2026.7.4 - @modelcontextprotocol/server-filesystem@2026.7.4 - @modelcontextprotocol/server-sequential-thinking@2026.7.4 - @modelcontextprotocol/server-memory@2026.7.4
github.com4 months agoView details
<details open> tests : disable backend sampler hip multi output (#26878) * test-backend-sampler: skip multi_output_sampling_chain on HIP The new multi_output_sampling_chain test uses top_k, whose backend probs path needs CUB (unavailable on HIP), so sampled_probs is null and the…
github.com2 months agoView details
<details open> ggml-hexagon: add HTP unary ops for ABS and LOG (#27786) Add HVX-accelerated implementations for GGML_OP_LOG and GGML_UNARY_OP_ABS on the HTP backend. - Register HTP_OP_UNARY_ABS and HTP_OP_UNARY_LOG in op_remap_to_htp() - Add ABS and LOG to ggml_backend_hexagon_d…
github.com2 months agoView details
## [3.6.0](https://github.com/openai/openai-python/compare/v3.5.0...v3.6.0) (2026-08-27) ### Features * **api:** add compute_units to Responses and Chat Completions usage ([#3749](https://github.com/openai/openai-python/issues/3749)) ([52421d1](https://github.com/openai/openai-p…
github.com2 months agoView details
<details open> jinja : fix quadratic cost in gather_string_parts (#27034) * jinja : fix quadratic cost in gather_string_parts * fix some comments * remove test </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-or…
github.com2 months agoView details
<details open> metal : add fa-vec tunings for M1 Ultra (#28088) * metal : add fa-vec tunings for M1 Ultra * metal : move M1 Ultra tunings after M1 Max section * metal : remove duplicate blank line </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.…
github.com2 months agoView details
langchain-ai/langchain langchain==1.4.0a1
Initial release fix(langchain): name the content type MCP conversion could not handle release(langchain): 1.4.0a1 test(langchain): skip MCP tests on a pydantic older than `mcp` supports test(langchain): drive MCP tests through FastMCP's own utilities fix(langchain/mcp): review e…
github.com2 months agoView details
<details open> llama: add token ID tracking to KV cell (#27762) * kv: track token id * rm get_prev_tokens, move it to the main pr * nits * add get_prev_tokens </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43…
github.com2 months agoView details
anthropics/anthropic-sdk-python v0.125.0
## 0.125.0 (2026-08-19) Full Changelog: [v0.124.0...v0.125.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.124.0...v0.125.0) ### Features * **api:** managed agents web search config and self hosted sandbox memory ([b75afd6](https://github.com/anthropics/anthropi…
github.com2 months agoView details
langchain-ai/langchain langchain-fireworks==1.6.1
Changes since langchain-fireworks==1.6.0 release(fireworks): 1.6.1 (#39975) fix(fireworks): drop reasoning history blocks (#39973) chore(model-profiles): refresh model profile data (#39844)
github.com2 months agoView details
<details open> metal : per-device tuned (Q, NE) for flash-attn vec (#26570) * metal : per-device tuned (Q, NE) for flash-attn vec (#25750) * rebase Q-generic FA vec body from 01dc93607 (#23114) * add 53 f16 (Q,NE) flash-attn vec instantiations (vec 80 -> 133) * add FA vec (Q,NE)…
github.com2 months agoView details
## [3.4.0](https://github.com/openai/openai-python/compare/v3.3.1...v3.4.0) (2026-08-25) ### Features * **api:** Add obfuscation field to ChatCompletionChunk ([#3690](https://github.com/openai/openai-python/issues/3690)) ([c7d8e1d](https://github.com/openai/openai-python/commit/…
github.com2 months agoView details
langchain-ai/langchain langchain-openai==1.6.0
Changes since langchain-openai==1.5.2 release(openai): 1.6.0 (#39762) feat(core): add standard model exception types (#39538) fix(openai): raise clear error on unexpected response type in `_create_chat_result` (#39731)
github.com2 months agoView details
## [2.53.0](https://github.com/openai/openai-python/compare/v2.52.1...v2.53.0) (2026-08-03) ### Features * **api:** Add gpt-5.5 and tool name/namespace to Responses types ([#3569](https://github.com/openai/openai-python/issues/3569)) ([dd1202d](https://github.com/openai/openai-p…
github.com3 months agoView details
langchain-ai/langchain langchain-anthropic==1.6.0
Changes since langchain-anthropic==1.5.6 release(anthropic): 1.6.0 (#39763) feat(core): add standard model exception types (#39538) fix(anthropic): exclude sibling directories from grep search scope (#39681) chore(infra): support langsmith gateway in CI (#39651)
github.com2 months agoView details
<details open> kleidiai: Rework KleidiAI Build System/Integration (#26077) * Rework KleidiAI Build System/Integration Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@arm.com> * Add fp16 guard, and fix cmake caching issue Signed-off-by: Jonathan Clohessy <Jonathan.Clohessy@ar…
github.com2 months agoView details
langchain-ai/langchain langchain-core==1.5.6
Changes since langchain-core==1.5.5 chore(core): release 1.5.6 (#39704) feat(core): incorporate gateway metadata to traces (#39703)
github.com2 months agoView details
# vLLM v0.27.0 Release Notes ## Highlights This release features 561 commits from 242 contributors (64 new)! * **Kimi K3 support** with a full stack landing in one release: core model files and kernels (#50089, #50000), Python (#50093) and Rust (#50104) frontends, AttnRes kernel…
github.com2 months agoView details
## [3.3.0](https://github.com/openai/openai-python/compare/v3.2.0...v3.3.0) (2026-08-18) ### Features * support named data-residency endpoints ([#3646](https://github.com/openai/openai-python/issues/3646)) ([11ee914](https://github.com/openai/openai-python/commit/11ee91475694d9c…
github.com2 months agoView details
<details open> model: add Kimi-K3 text model (#26185) * model: add Kimi-K3 text model Hybrid KDA (linear) + MLA (full) attention as in Kimi-Linear-48B, plus five things that architecture does not have: 1. cross-layer residual attention (attn_res_block_size) 2. latent MoE (routed…
github.com2 months agoView details
modelcontextprotocol/servers 2026.8.31
# Release : v2026.8.31 ## Updated packages - @modelcontextprotocol/server-filesystem@2026.8.31 - @modelcontextprotocol/server-memory@2026.8.31 - @modelcontextprotocol/server-sequential-thinking@2026.8.31 - @modelcontextprotocol/server-everything@2026.8.31
github.com2 months agoView details
anthropics/anthropic-sdk-python v1.2.0
## 1.2.0 (2026-08-27) Full Changelog: [v1.1.0...v1.2.0](https://github.com/anthropics/anthropic-sdk-python/compare/v1.1.0...v1.2.0) ### Features * **api:** beta files/skills namespaces use GA shapes; drop dated beta header pins ([9df4565](https://github.com/anthropics/anthropic-…
github.com2 months agoView details
<details open> server: re-design yield_to_queue thread model (#27133) * run common_speculative_process in worker * swap worker <--> main thread design </details> **Website:** - <https://llama.app> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.c…
github.com2 months agoView details
anthropics/anthropic-sdk-python v1.0.0
## 1.0.0 (2026-08-20) Full Changelog: [v0.125.0...v1.0.0](https://github.com/anthropics/anthropic-sdk-python/compare/v0.125.0...v1.0.0) ### ⚠ BREAKING CHANGES * **client:** upgrade to httpx2 and some minor breaking changes. See MIGRATION.md for details ### Features * **client:**…
github.com2 months agoView details
## [3.8.0](https://github.com/openai/openai-python/compare/v3.7.0...v3.8.0) (2026-09-03) ### Features * **api:** add gpt-6-astra and related features ([#3791](https://github.com/openai/openai-python/issues/3791)) ([09f446f](https://github.com/openai/openai-python/commit/09f446f5…
github.com2 months agoView details
<details open> bench: add --tensor-read-lazy (#27881) * bench: add --tensor-read-lazy * rm the alias * rename to LLAMA_LAZY_MODE_* </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/43739963> **macOS/iOS:** - [ma…
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.