3.46.0 (2026-11-05) Features api: add Australia, India, and Japan residency options (#4246) (2634b87) api: add GPT-6 Rosalind to the model catalog (#4243) (0f8e5f3) api: add image complexity and GIF and SVG output controls (#4247) (0152e3a) api: expand agent turn errors and image and audio options (#4245) (1b2fb74) Chores deps: bump github/codeql-action/init from 4.39.0 to 4.39.1 (#4230) (c9fe335)
[SDPA] Fix 32-bit key/value offset overflow in mem-efficient attentio…
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
Background op_overrides / op_allowlist / set_test_configs() (#176264, #181703, #181554) let out-of-tree (PrivateUse1) backends reuse OpInfo-based test suites through pure configuration. This PR brings @modules to parity with @ops. Changes Add module_overrides / module_allowlist to DeviceTypeTestBase and apply them in the modules parametrizer; Add a generic ModuleInfo.dtypesIf dict so any backend c…
Changes since langchain-core==1.7.5 release(core): 1.7.6 (#41698) perf(core): merge streamed AIMessageChunks once when accumulating runnable streams (#41697) perf(core): stop parse_partial_json from retrying one character at a time (#41467)
Fix ApproximateClockToUnixTimeConverter pre-calibration timestamp con…
Fixes #202777 Removing the small-input CPU fallback seems to improve performance on average, according to the following script (co-authored by Claude): Click to expand import argparse import itertools import torch import torch.utils.benchmark as benchmark SHAPES = [] for n in range(1, 112, 2): for b in range(1, 112, 10): if b * n * n < 12288: SHAPES.append((b, n, n)) DTYPES = { "float32": torch.fl…
Summary: The AVX2/AVX512 exp_u20 fast path builds 2^n by writing exponent bits, which cannot produce a subnormal, and it clamped at ln(FLT_MIN). So it returned 0 for every input whose exp is subnormal, and also for [-87.34, -86.99), where exp is still a normal float. It also turned NaN into exp(88.72). Fix the fast path instead of falling back to the scalar exp(): Split ln(2) (Cody-Waite) so the r…
Sdists rebuilt from main for /update on the CLAI bleeding channel. Not a release.
server : realtime: send an error event instead of crashing on exceptions (#31632) server : realtime: send an error event instead of crashing on exceptions server : route websocket handlers through ex_wrapper, remove the realtime test server : realtime: keep the previous tools when the chat template rejects new ones server : realtime: reject tool schemas the grammar cannot convert, drop ws_ex_wrapp…
opencl: improve decode perf with FA (#31633) opencl: use more workgroups for q4_K gate up + GLU Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com opencl: handle FA for GQA 2 and 6 with head size 256 Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com opencl: handle FA for GQA 16 with head size of 128, 512 Co-authored-by: Shaofei Qi shaoqi@qti.qualcomm.com opencl: handle FA for GQA 2 with head size…
model, mtmd: drama-3 tts support (#31613) model, mtmd: drama-3 tts support clean up mtmd: drama3 helper stops at the codebook tower limit Co-authored-by: Pascal admin@serveurperso.com Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/63780976 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
webgpu: return maxBufferSize from get_max_size and avoid whole-buffer bindings in memset/clear (#31348) Fix get_max_size and improve the memset shader Fix buffer_memset to handle the buffer size more than max binding size. Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/63772875 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI…
Release 0.168.0-alpha.2
Changes since langchain-fireworks==1.7.1 fix(fireworks): report streamed token usage once (#41693) release(fireworks): 1.7.2 (#41690) fix(fireworks): report the served model in response metadata (#41686) chore(model-profiles): refresh model profile data (#41669) fix(fireworks): promote reranking out of beta (#41551) chore(model-profiles): refresh model profile data (#41432) chore(infra): relax thi…
perf(vulkan): accelerate MOSS normalization and SiTU staging (#2273) Co-authored-by: mirek190 <mirek190@gmail.com>
Features api: add error details types and new error type values api: add ids filter to list workspaces client: add error classes for HTTP statuses and API error codes, and error_code, details and api_message on APIStatusError Bug Fixes api: capitalize CMEK in error details type names api: move some error details types to the resource they describe bedrock: raise a ValueError when model is "." or "…
What's Changed Changelog for v0.65.0 by @gemini-cli-robot in #29853 chore(release): bump version to 0.67.0-nightly.20261020.gb041de017 by @gemini-cli-robot in #29854 Changelog for v0.66.0-preview.0 by @gemini-cli-robot in #29852 feat(cli): bridge the IDE companion into container sandboxes over exec stdio by @elberthc-byte in #29858 fix(core): prevent duplicate agent loading when workspace is home…
No content.
What's Changed fix(overrides): forward arguments through patched get_headers by @jasonozuzu-cohere in #823 SDK regeneration by @fern-api[bot] in #824 Full Changelog: 7.2.0...7.3.1
What's Changed Changelog for v0.67.0-preview.0 by @gemini-cli-robot in #29990 Changelog for v0.66.0 by @gemini-cli-robot in #29992 docs(readme): clarify Gemini CLI scope, limitations, and tool landscape by @LyalinDotCom in #29995 fix(cli): bound inline history re-render after terminal width changes by @jvargassanchez-dot in #29904 fix(ui): handle surrogate pairs when truncating in sanitizeForDispl…
[fern-generated] Update SDK Generated by Fern CLI Version: unknown Generators: fernapi/fern-python-sdk: 5.41.10 [fern-replay] Applied customizations Patches with unresolved conflicts (3): patch-c81e8a75: fix(utils): embed(texts=[]) crashes with IndexError on empty input (#778) patch-41f344bd: feat(client): forward max_retries through Client/ClientV2 constructors (#779) patch-bc495daa: Omit Authori…
Verify this release cosign verify \ --key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \ ghcr.io/berriai/litellm:v1.106.7 Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images What's new in 1.106.7 We are readjusting how beta features work alongside LiteLLM, our core product. Starting with 1.106.7, the Lens b…
You can now work with GitHub Copilot directly in Xcode’s built-in coding assistant, bringing Copilot into your native Xcode workflow. The integration is now in public preview, available starting with… The post GitHub Copilot is now available in Xcode’s coding assistant appeared first on The GitHub Blog.
Release 0.167.0-alpha.3.1
This release introduces Qwen3.8-Flash-Next, polishes the Glass themes (now in Beta), adds a Composer position slider and lets models interact with files in the built-in browser. It also brings lower idle memory usage, preserved chat context when switching GGUF models, faster MLX loading and FP8 LoRA training. Highlights Qwen3.8-Flash-Next Dynamic V3.1 - 10-15% extra accuracy Guide Glass theme impr…