| Index | index by Group | index by Distribution | index by Vendor | index by creation date | index by Name | Mirrors | Help | Search |
| Name: gufo | Distribution: openSUSE Tumbleweed |
| Version: 0.28.0 | Vendor: openSUSE |
| Release: 1.1 | Build date: Fri Oct 30 15:33:55 2026 |
| Group: Unspecified | Build host: reproducible |
| Size: 105118425 | Source RPM: gufo-0.28.0-1.1.src.rpm |
| Packager: https://bugs.opensuse.org | |
| Url: https://github.com/gufo-org/gufo | |
| Summary: Local inference engine for AMD Strix Halo hardware | |
Gufo is a vertical local inference engine specifically built and optimized for AMD Strix Halo hardware (Ryzen AI MAX+ 395 systems with Radeon 8060S). It provides high-performance model serving with support for Qwen3.8, DeepSeek V4 Flash, MiniMax H3, Qwen3-TTS, and other models.
MIT
* Fri Oct 30 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.28.0
* embedding: per-request EmbeddingGemma 2 image budget (#870)
* embeddings: support video inputs (#869)
* qwen-image: stream safetensors weights, not mapping (#830)
* qwen: tune Qwen3.8-27B verification GEMM rows 2-8 (#874)
* Release notes: https://github.com/gufo-org/gufo/releases/tag/v0.28.0
- Update generated using pbuild-ai
* Fri Oct 30 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.27.0
* serve: add cache_persist=false to skip disk cache (#811)
* serve: support generated token logprobs (#814)
* loader: retry failed unbuffered weight reads (#858)
* qwen-flash: bound draft-ID remapping and blocks (#849)
* qwen-flash: preserve YaRN in batched MTP catch-up (#854)
* qwen38-flash-next: run Q8_0 weights on F32 kernels (#788)
* qwen38-flash-next: grow qfn_mmq stream arenas (#740)
* qwen: size Q8_0 prefill GEMM activation scratch (#777)
* qwen-flash: keep fused WMMA prefill past 262,144 (#866)
* qwen: run split K-quant prefill GEMM as 16-row pass (#779)
* Release notes: https://github.com/gufo-
org/gufo/releases/tag/v0.27.0
* Release notes: https://github.com/gufo-org/gufo/releases/tag/v0.27.0
- Update generated using pbuild-ai
* Wed Oct 28 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.26.0
* embedding: support native audio embeddings (#819)
* serve: add llama-server's /apply-template (#821)
* serve: let --cache-ram-bytes turn the RAM cache off (#783)
* serve: select EmbeddingGemma 2 checkpoint prompts by name (#823)
* audio: drop resident safetensors pages after the
TTS and ASR uploads (#845)
* build: load the patched ROCr from build-tree HIP binaries (#841)
* embedding: accept MP3s without a Xing header and
audio in llama.cpp multimodal_data (#828)
* qwen-flash: remove lossy chunked DeltaNet prefill (#850)
* qwen: keep model weights in device memory when the
heap has room (#708)
* rocm: qualify image, H3, DeepSeek and Qwen on 10.1 (#768)
* serve: accept more than 128 function tools (#827)
* server: drain the request before loading responder closes (#795)
* qwen-flash: faster Flash-Next prefill with chunked
DeltaNet and stream overlap (#758)
- Update generated using pbuild-ai
* Tue Oct 27 2026 Adrian Schröter <adrian@suse.de>
- use gcc 16 on Factory
* Mon Oct 26 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.25.0
* server: bound Qwen resolution for image_url.detail low (#774)
* serve: truncate over-length embedding inputs on request (#765)
* gcc16: force-include <format> before HIP headers (#782)
* qwen: fill device weights from shard file, not mapping (#794)
* embedding: batch concurrent requests on the device (#778)
* qwen: keep a stable cache boundary after system
instructions (#773)
* qwen: revert stable cache boundary after system
instructions (#815)
- Updated to version 0.24.0
* embeddings: support image inputs (#759)
* serve: allow repeated --served-model-name for one model (#736)
* serve: accept neutral llama.cpp sampler fields (#732)
* serve: stop counting a connection once response sent (#750)
* embedding: run EmbeddingGemma 2 attention on matrix cores (#770)
* docs: note client settings for LangChain and paperless-ngx (#785)
- Update generated using pbuild-ai
* Sun Oct 25 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.23.0
* embedding: serve EmbeddingGemma 2 on /v1/embeddings (#700)
* models: read model weights through the mapped_file leaf
(#738)
* platform: map GGUF shards through the mapped_file leaf (#734)
* embedding: tune GEMMs per shape with hipBLASLt (#751)
* qwen-flash: reduce selector spills and improve sampled
drafting (#742)
* qwen38_flash_next: let a lone greedy MTP request use
the small draft head (#733)
* qwen38_flash_next: let greedy requests with penalties or
constraints use the small draft head (#739)
* agents: describe where Windows portability code lives (#754)
- Update generated using pbuild-ai
* Fri Oct 23 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.22.0
* platform: add the net leaf (#711)
* platform: add the publish and prefault leaves (#729)
* platform: add the shutdown_signal leaf (#713)
* cache: free RAM before writing oversized checkpoints
to disk (#677)
* qwen38-flash-next: give each HIP stream its own
qfn_mmq scratch arena (#707)
* qwen38-flash-next: sum BF16 indexer projections
in K order for every token (#714)
* serve: accept standard image detail values as
automatic detail (#722)
* qwen38_flash_next: price unseeded sampled MTP drafts
at the decoding occupancy (#703)
- Update generated using pbuild-ai
* Fri Oct 23 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.21.0
* platform: add the os_info leaf (#709)
* qwen-flash: opt-in YaRN context extension (#350)
* bench: stop the benchmark server when startup interrupted (#702)
* qwen: reduce Flash-Next sampled decoding overhead (#699)
- Update generated using pbuild-ai
* Thu Oct 22 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.20.0
* cache: add Qwen 27B AR and DFlash2 cache continuation
* rocm: let DeepSeek V4 Flash load when weights exceed the
device pool
* serve: answer Expect: 100-continue before reading the body
* serve: report no content for whitespace between parallel tool
calls
* cache: avoid repeated resets and full checkpoint lookups
* qwen-flash: prefetch n-gram rows across cache checkpoints
* qwen38_flash_next: take the vector-load small projection path
for F16 and BF16 weights
- Update generated using pbuild-ai
* Wed Oct 21 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.19.0
* serve: report model, build, context, sessions and vision
in /props (#669)
* ci: refresh the release app token after waiting for release
checks (#665)
* ds4: stop the batched greedy DSpark frontier before an
accepted EOS (#668)
* qwen-flash: store d*sum(q) as the q8_1 block sum (#667)
* qwen-flash: let sampled requests use the small MTP draft
head on multi-session servers (#655)
* qwen27b: run verification attention rows > 1 as wave64
with shared per-head steps (#660)
* qwen38_flash_next: price greedy MTP drafts at the decoding
occupancy (#664)
* note Claude Code is unsupported with Qwen (#672)
- Update generated using pbuild-ai
* Tue Oct 20 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.18.0
* serve: honor the Messages thinking budget (#524)
* serve: prepare the structured-output vocabulary before serving
* cache: keep disk-cache snapshots out of the page cache (#477)
* ci: keep the devlab report when later jobs start (#659)
* qwen-flash: pin square-accumulation order in all
HcCombineMoeF16Kernel
instantiations (#624)
* qwen: reuse historical image preprocessing (#645)
* serve: reclaimable page cache is available in cgroup space (#637)
* tools: preserve optional arguments in native calls (#643)
* flash-next: reduce prompt and decode stalls (#653)
* qwen: fork the recurrent state across two buffers instead of
copying
it (#650)
- Update generated using pbuild-ai
* Mon Oct 19 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.17.1
* cache: reject capacity retries before reading payloads (#636)
(778061d)
* inference: reduce Flash-Next cache and cold-prompt stalls (#633)
(1f97092)
* qwen-flash: copy repeated context into MTP drafts (#613)
(8497711)
* qwen-flash: cut prefill and decode attention cost at depth (#626)
(5a1669a)
- Updated to version 0.17.0
* serve: prepare the Qwen vision sidecar before serving (#616)
(0604e9e)
* cache: bound publication waits by observed prefill cost (#621)
(e8e508f)
* cache: let disk eviction wait for startup orphan reclamation (#625)
(78248de)
* serve: keep the decimal spelling of integer JSON numbers (#614)
(22e3676)
* serve: preserve cache reuse when tool choice changes (#623)
(23d970d)
* qwen-flash: compact sparse attention selections once per row
(#622) (baf5a1b)
- Updated to version 0.16.0
* serve: keep /health answering while the model and disk tier load
(#610) (f6ca085)
* cache: reduce long-context checkpoint overhead (#615) (f8be547)
* qwen-flash: score MTP drafts over request vocabulary (#603)
(51a8b00)
* serve: move tool-call dialect parsing next to its renderers (#592)
(b6ba33d)
- Update generated using pbuild-ai
* Thu Oct 15 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.15.1
* cache: avoid artifact hashing for RAM-only Flash-Next (#602)
(43ad9a5)
* cache: repair flash-next functional cache regressions (#596)
(ec69aa3)
- Update generated using pbuild-ai
* Wed Oct 14 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.15.0
* serve: accept IPv6 listen addresses (#585) (a690704)
* cache: pin Flash-Next cache pages without compacting host memory
(#589) (10c40b0)
* serve: accept response schemas without additionalProperties (#582)
(c406e40)
* qwen-flash: speed up wide prefill kernels (#571) (a33e989)
- Updated to version 0.14.0
* cache: wire Flash-Next serving to the component cache (#573)
(058d6e8)
* rocm: managed-alloc fallback (#460) (248d902)
* update readme (#574) (8d4e1a2)
- Update generated using pbuild-ai
* Tue Oct 13 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.13.0
* exit as device_lost when generation stops making progress (#541)
* accept boolean or null stream on compatibility routes (#544)
* honor cache_prompt on raw completion routes (#557)
* use 128 n-gram readers for qwen-flash (#551)
* warn that automatic RAM budget ignores co-resident servers (#556)
* record rejected fork prefill kernels (#565)
- Update generated using pbuild-ai
* Mon Oct 12 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.12.0
* add Flash-Next continuation adapter for cache ([#536])
* accept image blocks in Messages user/tool results (#510)
* implement /v1/messages/count_tokens endpoint ([#512])
* keep mixed string/number enum values reachable ([#535])
* keep Flash-Next snapshots within device headroom ([#549])
* exclude cache reads from Messages input_tokens (#530)
* keep listening WebSocket clients past idle timeout (#527)
- Updated to version 0.11.0
* add committed HIP backing and transfer pools for cache (#504)
* define disk manifests and metadata startup index (#507)
* preserve borrowed rows while slots are idle (#505)
* publish checkpoints with crash-safe recovery (#509)
* select and evict resident and durable checkpoints (#517)
* stream checkpoints through bounded transfer pieces (#515)
keep a live frontier when branch restores borrowed checkpoint (#476)
- Updated to version 0.10.0
* support tools and streaming on /v1/messages (#469)
* accelerate prefill and MTP catch-up for qwen-flash (#485)
* unroll the fused attention value halves for qwen-image (#481)
* keep the 8-row IQ2 gate/up tiles out of scratch (#482)
* add cache redesign implementation cards and RFC (#489)
- Updated to version 0.9.1
* drop the fixed 1 GiB cap on automatic disk staging (#473)
* keep prefill GEMMs spill-free on clang 23 for hip (#459)
use 4096-token prefill chunks with overlapped gather (#470)
* centralize control-token literals in one header (#464)
- Updated to version 0.9.0
* add opt-in --trace for text request content (#458)
* exclude free CMA pages from the automatic RAM budget (88d2139)
* keep learned branch points under RAM pressure (#466)
* default the per-client queue cap to --max-pending (#467)
* hoist mid-conversation system messages to leading block (#449)
* reduce prefill work at long context for qwen-flash (#463)
* avoid flash-next prompt checkpoint copies for qwen (#445)
- Updated to version 0.8.1
* keep tool calls in native model syntax (#441)
* remove leading answer blank lines after reasoning (#446)
* accept image histories within model context (#447)
- Update generated using pbuild-ai
* Mon Oct 05 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.8.0
* added OpenAI Responses compatibility (#434)
- Updated to version 0.7.1
* keep stable checkpoint before replaced trailing user context (#407)
* accept reasoning fields Claude Code sends to /v1/messages (#405)
* preserve active disk-cache writes during startup (#392)
* reclaim output capacity from abandoned streams (#394)
* end DeepSeek tool output after the call block (#397)
* keep DeepSeek client markup as content, as llama.cpp does (#420)
* keep tool-call framing out of assistant content (#400)
* preserve literal reasoning tags when thinking is disabled (#391)
- Updated to version 0.7.0
* learn shared-prefix boundaries in the RAM cache (#386)
* let an explicit RAM cache limit exceed the automatic budget (#384)
* report live sessions and llama.cpp-compatible metrics (#389)
* export speculative verification round metrics (#403)
* detect idle GPU loss and defer streaming success (#406)
* parse tool output using the admitted request format (#393)
* reuse replayed tool turns with union and typed arguments (#404)
- Updated to version 0.6.0
* share in-flight prefixes between concurrent requests (#382)
* exit and report device_lost when GPU context is lost (#390)
* improve error messaging on streaming generation failure (#385)
* preserve JSON string ownership during tool recovery (#396)
* separate Messages thinking blocks and accept the thinking field (#380)
- Updated to version 0.5.0
* accept WebP and other spellings of image data URLs (#352)
* keep cache reuse advancing as conversations grow (#358)
* keep cached conversations independent of execution sessions (#369)
* retain prefixes across conversation history edits (#362)
* prevent source-noise reuse in image edits (#377)
* advertise loaded model input modalities (#367)
* keep literal tool markers inside constrained reasoning (#361)
* preserve native tool schemas and historical calls (#373)
- Update generated using pbuild-ai
* Thu Oct 01 2026 Adrian Schröter <adrian@suse.de>
- Updated to version 0.4.0
* expose live token and request metrics in serve ([#351])
* report cache eviction and retained snapshot capacity ([#353])
* make log verbosity configurable with --log-level ([#319])
* support llama-server return_progress on streaming (#344)
* preserve seeded MTP replay across cache reuse (qwen-flash) ([#330])
* preserve native tool calls during constrained decoding ([#324])
* keep SSE streams alive during generation ([#334])
* accelerate greedy penalties and fix sampling ranges (qwen-flash) (#332)
* explain how the KV cache works in gufo ([#360])
- Update generated using pbuild-ai
* Wed Sep 30 2026 Adrian Schröter <adrian@suse.de>
- Initial package of gufo 0.2.0
Gufo is a local inference engine optimized for AMD Strix Halo
hardware that enables running large language and text-to-speech
models directly on your device. It provides a high-performance
server for seamless AI model serving without relying on cloud
services.
- Generated using pbuild-ai
/usr/bin/gufo /usr/bin/gufo-server /usr/lib/systemd/system-preset/90-gufo.preset /usr/lib/systemd/system/gufo.service /usr/lib/sysusers.d/gufo-user.conf /usr/share/doc/packages/gufo /usr/share/doc/packages/gufo/LICENSE /usr/share/doc/packages/gufo/NOTICE /usr/share/doc/packages/gufo/THIRD_PARTY_NOTICES.md /usr/share/doc/packages/gufo/docs /usr/share/doc/packages/gufo/docs/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/CI.md /usr/share/doc/packages/gufo/docs/CLI.md /usr/share/doc/packages/gufo/docs/DEVELOPMENT.md /usr/share/doc/packages/gufo/docs/KV-CACHE.md /usr/share/doc/packages/gufo/docs/PERFORMANCE.md /usr/share/doc/packages/gufo/docs/RELEASING.md /usr/share/doc/packages/gufo/docs/SERVER.md /usr/share/doc/packages/gufo/docs/TESTING.md /usr/share/doc/packages/gufo/docs/cache-redesign /usr/share/doc/packages/gufo/docs/cache-redesign/RFC.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards /usr/share/doc/packages/gufo/docs/cache-redesign/cards/01-functional-coverage.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/02-package-and-adapter-api.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/03-resource-ledger.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/04-chunks-and-checkpoints.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/05-prefix-index-and-lookup.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/06-slot-leases-and-mutation.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/07-retention-policy.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/08-committed-backing-and-streams.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/09-idle-spill.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/10-disk-format-and-index.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/11-publication-and-crash-safety.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/12-streamed-transfers.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/13-tiered-lookup-and-eviction.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/14-flash-next-adapter.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/15-qwen27b-ar-adapter.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/16-qwen27b-dflash2.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/17-deepseek-adapter.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/18-non-continuation-records.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/19-switch-over.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/20-e2e-baseline-and-qualification.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/21-edit-boundary-admission.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/22-small-budget-retention.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/README.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/d1-transition.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/d2-first-mode.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/d3-step-baselines.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/d4-options-and-budgets.md /usr/share/doc/packages/gufo/docs/cache-redesign/cards/todo.md /usr/share/doc/packages/gufo/docs/cache-redesign/measurements /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/08-gfx1151.csv /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/09-gfx1151.csv /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/09-initial-gfx1151.csv /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/09-review1-gfx1151.csv /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/12-gfx1151.csv /usr/share/doc/packages/gufo/docs/cache-redesign/measurements/13-gfx1151.csv /usr/share/doc/packages/gufo/docs/models /usr/share/doc/packages/gufo/docs/models/README.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/QUALITY.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/README.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/ROCM.md /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/antirez-ds4-ar-comparison.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/bench.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/captured-operator-audit.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/loading.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/memory.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/multi-ar.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/multi-dspark.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/single-ar.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/charts/single-dspark.svg /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/cost-calibration.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/dspark-sampling.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/indexer-boundary.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/loading-gufo.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/loading-reference.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/memory-gufo.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/memory-reference.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/model-identities.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-ar-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-ar-reference.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-mixed-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-mixed-gufo-dspark.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-repetition-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/multi-repetition-gufo-dspark.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/prefill-formula-audit.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/quality-qualification.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/reference-qualification.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/reference-smoke.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/single-ar-gufo.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/single-ar-reference.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/single-dspark-gufo.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/single-dspark-repetition-gufo.json /usr/share/doc/packages/gufo/docs/models/deepseek-v4-flash/artifacts/unavailable.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2 /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/QUALITY.md /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/README.md /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/ROCM.md /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-23-gemm-ab.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-23-nix.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-24-attention-ab.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-24-batching-ab.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-24-images.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-26-audio.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-29-video-ci.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-2026-10-29-video.json /usr/share/doc/packages/gufo/docs/models/embeddinggemma-2/artifacts/gfx1151-pr759-review.json /usr/share/doc/packages/gufo/docs/models/minimax-h3 /usr/share/doc/packages/gufo/docs/models/minimax-h3/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/minimax-h3/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/minimax-h3/QUALITY.md /usr/share/doc/packages/gufo/docs/models/minimax-h3/README.md /usr/share/doc/packages/gufo/docs/models/minimax-h3/ROCM.md /usr/share/doc/packages/gufo/docs/models/minimax-h3/artifacts /usr/share/doc/packages/gufo/docs/models/minimax-h3/artifacts/full-resolution-kernels.json /usr/share/doc/packages/gufo/docs/models/minimax-h3/artifacts/native-attention.json /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1 /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/QUALITY.md /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/README.md /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/ROCM.md /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/artifacts /usr/share/doc/packages/gufo/docs/models/qwen-image-2.1/artifacts/qualification.json /usr/share/doc/packages/gufo/docs/models/qwen3-asr /usr/share/doc/packages/gufo/docs/models/qwen3-asr/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/qwen3-asr/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/qwen3-asr/QUALITY.md /usr/share/doc/packages/gufo/docs/models/qwen3-asr/README.md /usr/share/doc/packages/gufo/docs/models/qwen3-asr/ROCM.md /usr/share/doc/packages/gufo/docs/models/qwen3-asr/artifacts /usr/share/doc/packages/gufo/docs/models/qwen3-asr/artifacts/native-convolution.json /usr/share/doc/packages/gufo/docs/models/qwen3-tts /usr/share/doc/packages/gufo/docs/models/qwen3-tts/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/qwen3-tts/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/qwen3-tts/QUALITY.md /usr/share/doc/packages/gufo/docs/models/qwen3-tts/README.md /usr/share/doc/packages/gufo/docs/models/qwen3-tts/ROCM.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/CONTINUATION-ADAPTER.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/QUALITY.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/README.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/ROCM.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/bench.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/loading.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/memory-q4.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/memory-q8.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/multi-ar-q4.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/multi-ar-q8.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/multi-dflash2-q4.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/multi-dflash2-q8.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/single-ar-q4.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/single-ar-q8.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/single-dflash2-q4.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/charts/single-dflash2-q8.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/component-cache-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/loading-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/loading-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/memory-q4-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/memory-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/memory-q8-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/memory-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/model-identities.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-ar-q4-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-ar-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-ar-q8-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-ar-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q4-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q4-gufo-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q4-reference-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q8-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q8-gufo-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q8-reference-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-mixed-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q4-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q4-gufo-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q4-reference-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q8-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q8-gufo-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/multi-repetition-q8-reference-dflash2.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-ar-c1-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-ar-c1-pruning.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-c2-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-c4-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-c6-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-c8-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q4-dflash2-c1-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/q8-tg-focused.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/quantization-quality.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/recurrent-fork-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-ar-q4-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-ar-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-ar-q8-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-ar-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-q4-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-q8-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-repetition-q4-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-repetition-q4-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-repetition-q8-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/single-dflash2-repetition-q8-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/speculative-adaptive-corpus.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-27b/artifacts/speculative-corpus.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/BENCHMARKS.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/CONTINUATION-ADAPTER.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/EXPERIMENTS.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/PROMPT-CHECKPOINTS.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/QUALITY.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/README.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/ROCM.md /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/attention-tiles-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/bench.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/cache-checkpoint-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/loading.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/memory.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/multi-ar.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/multi-mtp.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/single-ar.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/charts/single-mtp.svg /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/decode-kernels-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/functional-fixes.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/host-memory-stalls-review.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/loading-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/loading-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/memory-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/memory-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/model-identities.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/mtp-cache-replay.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-ar-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-ar-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-mixed-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-mixed-gufo-mtp.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-mixed-reference-mtp.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-repetition-gufo-ar.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-repetition-gufo-mtp.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/multi-repetition-reference-mtp.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/penalty-verification.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/prefill-deep-context.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/prefill-final-rows.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/prefill-long-context.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/prefill-normalization.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-ar-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-ar-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-mtp-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-mtp-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-mtp-repetition-gufo.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/single-mtp-repetition-reference.json /usr/share/doc/packages/gufo/docs/models/qwen3.8-flash-next/artifacts/vision-parity.json /usr/share/fillup-templates/sysconfig.gufo /usr/share/gufo /usr/share/gufo/eval /usr/share/gufo/eval/antirez-ds4.json /usr/share/gufo/models /usr/share/gufo/models/minimax_h3 /usr/share/gufo/models/minimax_h3/MINIMAX_H3_FL2VA_BF16.source-manifest.json /usr/share/licenses/gufo /usr/share/licenses/gufo/LICENSE /usr/share/licenses/gufo/NOTICE /usr/share/licenses/gufo/THIRD_PARTY_NOTICES.md /usr/share/licenses/gufo/third-party /usr/share/licenses/gufo/third-party/DS4-GB10.txt /usr/share/licenses/gufo/third-party/LICENSE.ds4 /usr/share/licenses/gufo/third-party/ccv.txt /usr/share/licenses/gufo/third-party/composable_kernel.txt /usr/share/licenses/gufo/third-party/curl.txt /usr/share/licenses/gufo/third-party/ffmpeg-GPL-3.0.txt /usr/share/licenses/gufo/third-party/ffmpeg-LGPL-3.0.txt /usr/share/licenses/gufo/third-party/ffmpeg.txt /usr/share/licenses/gufo/third-party/h3.c.txt /usr/share/licenses/gufo/third-party/hip.txt /usr/share/licenses/gufo/third-party/hipblas.txt /usr/share/licenses/gufo/third-party/hipblaslt.txt /usr/share/licenses/gufo/third-party/hipcub.txt /usr/share/licenses/gufo/third-party/icu.txt /usr/share/licenses/gufo/third-party/libjpeg-turbo-IJG.txt /usr/share/licenses/gufo/third-party/libjpeg-turbo.txt /usr/share/licenses/gufo/third-party/libpng.txt /usr/share/licenses/gufo/third-party/libsndfile.txt /usr/share/licenses/gufo/third-party/libsoxr.txt /usr/share/licenses/gufo/third-party/llama.cpp.txt /usr/share/licenses/gufo/third-party/llvm-openmp.txt /usr/share/licenses/gufo/third-party/openssl.txt /usr/share/licenses/gufo/third-party/qwen.txt /usr/share/licenses/gufo/third-party/rocblas.txt /usr/share/licenses/gufo/third-party/rocprim.txt /usr/share/licenses/gufo/third-party/rocwmma.txt /usr/share/licenses/gufo/third-party/strix-halo-llamacpp.txt
Generated by rpm2html 1.8.1
Fabrice Bellet, Thu Nov 12 01:39:22 2026