Changelog
Every update, noted here. GitHub Atom
- Strata 0.1.44.12026-10-14
A hotfix for 0.1.44: PCs with an older CPU start again, CUDA 12.0 / 12.1 toolkits can build the engine, and Apple M2 Macs give correct answers. Answers are the same as 0.1.44 (byte-identical in our identity tests on…
- Strata 0.1.442026-10-13
Update: the issues found right after this release (Macs other than M4/M5, building with CUDA 12.1, Pascal cards on CPUs without AVX) are fixed in [0.1.44.1](https://github.com/Niko1221/Strata/releases/tag/v0.1.44.1).…
- Strata v0.1.43.12026-10-12
A hotfix for 0.1.43: Linux NVIDIA decode is fast again on desktops (the adaptive overlap is opt-in again), long prompts no longer stall on Windows and SATA SSDs, two-card batch serving is about 35% faster again, RX 6000…
- Strata v0.1.432026-10-11
Faster decode and prompts on NVIDIA, AMD and Intel, plus the fixes since 0.1.42. Decode is up to 38% faster on a 16 GB Radeon, 5-11% on RTX 30-series and Tesla P100 under Linux, up to 19% on four Radeons, and 14-21% on…
- Strata v0.1.422026-10-10
About 13-16% faster decode on one NVIDIA GPU or a layer split, up to 30% more on a single card whose CPU outruns its PCIe link, a long list of fixes for multi-GPU splits, Windows AMD, Intel Arc and tight-RAM machines,…
- Strata v0.1.412026-10-08
Faster on more than one GPU, faster short prompts on NVIDIA, about twice as fast prompts on Windows with little RAM, and a long list of fixes. Two defaults change: --batch on a layer split now runs one pipeline group…
- Strata v0.1.40.42026-10-08
Hotfix for 0.1.40.3: decode on Pascal cards (Tesla P40, GTX 1080, GTX 1070) is back to the 0.1.40 speed. Default answers are unchanged. Update with UPDATE.bat (Linux: ./update.sh); setup replaces the engine with…
- Strata v0.1.40.32026-10-07
Hotfix for 0.1.40.2: Intel Arc install and A-series fixes, Windows AMD speed and runtime fixes, Docker config links, and a few smaller fixes. Default answers are unchanged. Update with UPDATE.bat (Linux: ./update.sh);…
- Strata v0.1.40.22026-10-07
Faster and fixed across the board: official Intel Arc support (Arc Pro B70 and A750 tested), bug fixes and speed-ups merged from the open issues and PRs, and big gains on multi-GPU, low-RAM Linux and long-document use.…
- Strata v0.1.40.12026-10-06
Hotfix for 0.1.40: a tool call that is only quoted (in the thinking or in a code block) no longer runs, and requests waiting during an engine restart no longer hang. Python server fixes only. The engine is the same as…
- Strata v0.1.402026-10-06
Strix Halo (gfx1151) support, crash, NaN and security fixes, better multi-GPU, batching and resident modes, Q4_0 / Q4_1 and more PLE table formats, AMD fixes, a much faster Linux cold start, and a long list of opt-ins.…
- Strata v0.1.392026-10-04
Faster decode and long prompts, several requests at once, older and other hardware as experimental opt-ins, the OpenAI Responses API for Codex, a fix for slower prompts with a RAM budget, and a batch of fixes from your…
- Strata v0.1.382026-10-03
Faster prompts, --kv q4_0 prompts on tensor cores, a 6 GB card that starts, and a large batch of community PRs. Security: the server without an API key (DNS rebinding, cross-site requests). Without api_key, the server…
- Strata v0.1.372026-10-02
A frozen engine no longer hangs the server, Windows AMD counts the desktop's VRAM, and a batch of setup fixes from your reports. The server notices a silent engine (481): if the engine prints nothing during a request…
- Strata v0.1.362026-10-02
Faster: Q2_0 reads prompts 16-22% faster and writes up to 18% faster at long contexts. Plus one-click updates (UPDATE.bat), an opt-in memory of which experts you use, and clearer logs. Speed (136), measured on an RTX…
- Strata v0.1.352026-10-02
Windows AMD no longer crashes on the first prompt, the low-RAM mode works on 32 GB Windows PCs, and a batch of fixes from your reports. AMD on Windows (468, 461): the engine now uses the HIP runtime it ships with.…
- Strata v0.1.342026-10-02
AMD cards on Windows (new), an MCP server so your AI assistant can set Strata up, a shorter README - and a cancelled request now frees the engine within a second. AMD on Windows (new, 247 325): an AMD card on Windows is…
- Strata v0.1.332026-10-01
The image encoder runs on every CPU again, and setup recommends instead of forcing: a longer context, more GPUs or a bigger RAM budget you choose is kept, with a note about the risk. Images (411, 412): 0.1.32's…
- Strata v0.1.322026-10-01
Multi-GPU short prompts fixed, AMD decode +12%, Unsloth's Q4 model in setup with 2.8x faster prompts, and 30+ community changes - with the same answers. Multi-GPU: short prompts faster again (340, riverhh76). Since…
- Strata v0.1.312026-10-01
Unsloth's Q4 model runs on a 64 GB PC (experimental), AMD decode up to 15% faster, models load twice as fast on Windows, and a batch of fixes. Experimental: Unsloth UD-Q4_K_XL on a normal PC. Strata can now run…
- Strata v0.1.302026-09-30
Short prompts up to 28% faster (the same answers), multi-GPU and AMD RDNA4 improvements, a server that can give the GPU back, and several opt-in features. Faster short prompts. Prompts of 1K to 4K tokens read all…
- Strata v0.1.292026-09-30
Sampled answers up to 40% faster (the same text), faster prompt kernels, correctness fixes, and several contributions. Sampled answers (197, @gputier). With a temperature above 0 (most chat apps), each token's top-k…
- Strata v0.1.282026-09-30
Fixes: VRAM left free again after 0.1.27's larger draft head, a cancelled request no longer kills the next one, and the API key protects every endpoint. VRAM (199, 201, 217). The expert cache takes the free VRAM minus a…
- Strata v0.1.272026-09-29
Answers in Chinese, Japanese or Korean are written faster, RTX 20 cards are supported, and five fixes. Faster CJK answers (137). The draft layer (MTP speculative decoding) can only propose tokens from its subset of the…
- Strata v0.1.262026-09-29
Prompts up to 32K read 4-10% faster: the draft layer's prompt pass runs in batches. Before answering, Strata runs its draft layer over the prompt, so the drafter (MTP speculative decoding) knows the conversation. That…
- Strata v0.1.252026-09-29
Faster prompts, AMD Radeon support (experimental), and a smaller KV cache option. Faster prompts (same output): reading a prompt got 7% faster. RTX 5070, Q2_0: - 32K tokens: 1,901 → 2,030 tokens/s. - 128K tokens: 1,955…
- Strata v0.1.242026-09-29
Long prompts read faster: the sparse attention's selection runs on tensor cores. For every token of a prompt, Strata picks which earlier parts of the context its attention reads (the QSA selection). At long context that…
- Strata v0.1.232026-09-29
Faster decoding, llama.cpp-compatible server endpoints, and fixes for images, 8 GB cards and multi-GPU. Faster answers: the verify window's per-token kernels (router, norms, RoPE, the shared-expert cast, the combine)…
- Strata v0.1.222026-09-29
Faster prompts, and several GPUs without typing any flags. Prompts are read faster (RTX 5070, Q2_0): a 32K-token prompt 1,213 → 1,646 tokens/s, a 128K prompt with KV streaming 1,144 → 1,596 tokens/s (time to first token…
- Strata v0.1.212026-09-29
One model across two or three NVIDIA cards (experimental). - Layer split across GPUs: - Setup: START-HERE.bat --setup --gpus 0,2 (Linux: ./setup.sh --setup --gpus 0,2), or "gpu": [0, 2] in a run config. - Each card runs…