zhifu gao
c4a8ab1c2c
Merge pull request #3597 from modelscope/codex/fix-vllm-fp16-3595
...
fix(fun-asr-nano): stabilize fp16 vLLM decoding
2026-09-01 15:08:16 +08:00
LauraGPT
f5fcb6478e
ci: validate Fun-ASR-Nano vLLM contracts
...
Signed-off-by: LauraGPT <[email protected]
2026-09-01 07:05:52 +00:00
LauraGPT
e7ddad713e
feat: serve MOSS diarization across deployment stack
...
Signed-off-by: LauraGPT <[email protected]
2026-09-01 03:02:33 +00:00
LauraGPT
94e07f85da
ci(release): attach Python packages automatically
...
Signed-off-by: LauraGPT <[email protected]
2026-08-30 20:47:50 +00:00
LauraGPT
144d2db5f1
ci: cache online CPU Docker layers
...
Signed-off-by: LauraGPT <[email protected]
2026-08-30 18:42:36 +00:00
LauraGPT
de55ad1c69
feat(runtime): add online CPU source Dockerfile
...
Signed-off-by: LauraGPT <[email protected]
2026-08-30 17:38:47 +00:00
LauraGPT
c0b0174738
fix(runtime): bundle Windows CUDA dependencies
...
Signed-off-by: LauraGPT <[email protected]
2026-08-30 02:34:31 +00:00
LauraGPT
c567595900
feat(runtime): add Windows Blackwell CUDA asset
...
Signed-off-by: LauraGPT <[email protected]
2026-08-30 01:48:01 +00:00
LauraGPT
754ddc2bac
ci(moss): pin formatter version
...
Signed-off-by: LauraGPT <[email protected]
2026-08-29 15:58:04 +00:00
LauraGPT
9115b95882
ci(moss): validate adapter contracts
...
Signed-off-by: LauraGPT <[email protected]
2026-08-29 15:56:13 +00:00
zhifu gao
4df59cc153
chore(release): prepare 1.4.5 ( #3534 )
...
Publish the optional-torchaudio inference path, pin the verified nine-platform llama.cpp runtime matrix, and document the protected exact-main publication gate.
Signed-off-by: LauraGPT <[email protected]
2026-08-28 00:59:31 +08:00
Kobi Hikri
6570924ed0
ci: publish MCP server images with SBOM attestations ( #3437 )
...
* ci: attach provenance and SBOM attestations to the published MCP server image
* ci: restore trailing newline at end of file
2026-07-29 20:08:47 +08:00
zhifu gao and LauraGPT
84e049ed48
feat(site): launch the FunASR deployment product hub ( #3424 )
...
* docs: design product deployment hub
* docs(site): plan deployment product hub implementation
* feat(site): add deployment evidence registry
* feat(site): add deployment recommendation engine
* build(site): track reproducible live-site corpus
* feat(site): build bilingual deployment product surface
* feat(site): add deployment contracts and benchmarks
* feat(site): preserve legacy routes and unify navigation
* ci(site): validate reproducible product builds
* ops(site): add atomic releases and hardened nginx
* test(site): add responsive product browser coverage
* fix(site): support managed and manual nginx masters
* fix(site): make release smoke routes configurable
* docs(site): record product hub rollout
---------
Co-authored-by: LauraGPT <[email protected]
2026-07-27 01:45:30 +08:00
zhifu gao and zhifu gao
ac0a08de47
release: attach runtime assets to Python releases ( #3405 )
...
Co-authored-by: zhifu gao <[email protected]
2026-07-24 06:34:31 +08:00
zhifu gao
9b918d74d7
feat(runtime): publish Windows Vulkan binary ( #3398 )
...
* feat(runtime): add Windows Vulkan release asset
* fix(ci): install SPIR-V headers for Windows Vulkan
* fix(runtime): make Windows Vulkan package standalone
2026-07-23 18:49:28 +08:00
zhifu gao
147a132cf7
Harden MCP registry publication ( #3389 )
2026-07-23 12:02:35 +08:00
zhifu gao
c3342f31ee
ci: add runtime downloads to package releases
...
Ensure package releases link the current llama.cpp runtime assets.
2026-07-23 00:41:34 +08:00
zhifu gao
c7f6edb9e6
docs(runtime): mention Vulkan asset in release notes
...
Keep generated runtime release notes aligned with the new Linux Vulkan asset.
2026-07-22 18:44:03 +08:00
zhifu gao
e3327be1bd
feat(runtime): add Vulkan llama.cpp backend packaging
...
Add Linux Vulkan packaging and runtime selection for the FunASR llama.cpp SenseVoice GGUF backend.
2026-07-22 18:40:34 +08:00
zhifu gao
f1e287edc2
Add Windows CUDA llama.cpp release asset
...
Adds a Windows x64 CUDA release asset for the llama.cpp SenseVoice runtime, with CUDA Toolkit setup, architecture-86 build flags, focused SenseVoice target packaging, docs, and workflow regression tests. Manual workflow dispatch 29656771776 passed all build matrix jobs including build-windows-x64-cuda.
2026-07-19 03:24:07 +08:00
zhifu gao
2792c98470
Release funasr-onnx 0.4.2 without Torch runtime dependency ( #3242 )
...
* Release funasr-onnx 0.4.2 candidate
* Use Node 24 release validation actions
* Harden release dependency parsing
2026-07-17 17:24:02 +08:00
zhifu gao
68a21aafbb
docs(llama.cpp): fix default GGUF quickstart ( #3234 )
...
* docs(llama.cpp): fix default GGUF quickstart
Signed-off-by: 游雁 <[email protected] [email protected] [email protected] [email protected] [email protected]
2026-07-15 20:15:07 +08:00
游雁
9c17931645
fix(llama.cpp): download one GGUF variant by default
2026-07-15 04:28:57 +00:00
zhifu gao
ddd9a3fada
Publish FunASR MCP server to the official Registry ( #3228 )
...
Add versioned OCI metadata, GHCR and OIDC release automation, strict container smoke tests, and release documentation.
2026-07-15 05:27:12 +08:00
zhifu gao
1c22668808
ci: publish AVX2 llama.cpp runtime assets
2026-06-29 21:15:52 +08:00
zhifu gao
0f655f27ea
ci: build portable llama.cpp release binaries ( #3037 )
...
Disable native ggml CPU tuning and high ISA flags for generic llama.cpp release assets so prebuilt binaries do not depend on the CI runner CPU instruction set.
2026-06-29 01:20:38 +08:00
zhifu gao
6840f0f504
ci: drop macos-x64 (Intel runner unavailable; arm64 covers modern Macs)
2026-06-20 15:29:18 +08:00
zhifu gao
9345742076
ci: limit build parallelism (-j 2) to avoid OOM on runners
2026-06-20 14:40:54 +08:00
zhifu gao
b9024790c7
ci: cross-platform prebuilt binary release for llama.cpp runtime ( #3001 )
2026-06-20 14:21:14 +08:00
zhifu gao
59bd7325bb
ci: auto-create GitHub Release on version tag push ( #2995 )
2026-06-19 22:01:50 +08:00
zhifu gao
d0da2adfd0
docs: add migration benchmark issue template
...
Add a dedicated migration benchmark report template and link it from migration docs and examples.
2026-05-25 11:26:35 +08:00
zhifu gao
46de9bfc9d
docs: add community showcase issue template
...
Add a template and docs links for collecting FunASR demos, production stories, and benchmark reports.
2026-05-24 23:38:40 +08:00
zhifu gao
ba2b488e17
docs: add community growth and contribution guides
...
Merge pull request #2863 from codex/growth-20k
2026-05-24 20:29:56 +08:00
游雁
3b608cf9e1
docs: fix GitHub Pages API publishing flow
2026-05-21 13:05:46 +00:00
游雁
abffaa59f6
ci: add GitHub Actions workflow for auto-updating API docs on code changes
...
- scripts/gen_api_docs.py: generates API HTML with source code + GitHub links
- .github/workflows/update-api-docs.yml: triggers on funasr/**/*.py changes
- Auto-deploys to gh-pages branch
2026-05-21 11:31:42 +00:00
zhifu gao
68f0603b10
Dev gzf ( #1475 )
...
* qwenaudio qwenaudiochat
* qwenaudio qwenaudiochat
* whisper
* whisper
* llm
* llm
* llm
* llm
* llm
* llm
* llm
* llm
* export onnx
* export onnx
* export onnx
* dingding
* dingding
* llm
* doc
* onnx
* onnx
* onnx
* onnx
* onnx
* onnx
* v1.0.15
* qwenaudio
* qwenaudio
* issue doc
2024-03-12 09:23:04 +08:00
游雁
f3c79b4968
update
2024-02-20 14:05:11 +08:00
游雁
94de39dde2
aishell example
2024-02-19 22:21:50 +08:00
游雁
546e3a432c
raise issues
2024-01-16 14:28:53 +08:00
haoneng.lhn
3d17f80b99
update github io
2023-10-11 16:24:22 +08:00
游雁
5e90775d98
docs
2023-07-25 10:44:52 +08:00
游雁
d29e826f2c
docs
2023-07-24 21:33:41 +08:00
yhliang
4533ada888
remove _build ( #773 )
...
* remove build files
* fix workflow
* fix docs
* fix docs
* fix docs
* fix workflow
2023-07-24 16:50:09 +08:00
嘉渊
a43b3da4be
update
2023-07-05 21:55:40 +08:00
嘉渊
9dc9482300
update repo
2023-06-14 16:13:59 +08:00
嘉渊
fee48e7a62
update repo
2023-06-14 15:02:38 +08:00
yhliang
3ef7c5c966
update readme
2023-04-25 17:23:12 +08:00
游雁
6ff262c318
docs
2023-04-19 14:41:37 +08:00
游雁
81e56b2627
docs
2023-04-19 14:39:22 +08:00
yhliang
15b8b7bd20
Merge branch 'dev_lyh' into main
2023-04-18 19:19:48 +08:00
zhifu gao