LauraGPT
b4018dacae
test: track current llama.cpp runtime contract
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-17 00:46:25 +00:00
zhifu gao
7825bbbe09
Merge pull request #3503 from modelscope/codex/openmaic-ecosystem-20260817
...
docs: feature OpenMAIC local FunASR integration
2026-08-17 08:36:50 +08:00
LauraGPT
fa2bb1c28e
docs: feature OpenMAIC local FunASR integration
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-17 00:32:51 +00:00
zhifu gao
2e8873a2a1
Merge pull request #3502 from modelscope/codex/growth-ledger-vision-3496-20260817
...
docs: refresh ecosystem growth operations
2026-08-17 08:11:50 +08:00
LauraGPT
2c44e898a2
docs: refresh ecosystem growth operations
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-17 00:10:26 +00:00
zhifu gao
9c6df1784c
Merge pull request #3501 from modelscope/codex/docs-mlx-ecosystem-20260817
...
docs: publish MLX Audio Fun-ASR integration
2026-08-17 06:09:18 +08:00
LauraGPT
89a761ed67
docs: publish MLX Audio Fun-ASR integration
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-16 22:05:25 +00:00
zhifu gao and LauraGPT
d7178079e0
docs: correct product site capability claims ( #3500 )
...
Signed-off-by: LauraGPT <[email protected] >
Co-authored-by: LauraGPT <[email protected] >
2026-08-17 05:44:58 +08:00
zhifu gao
4df55195b3
Merge pull request #3499 from modelscope/codex/site-official-repo-footer-20260817
...
docs(site): surface official repositories in footer
2026-08-17 04:55:50 +08:00
LauraGPT
7db30d2e95
docs(site): surface official repositories in footer
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-16 20:51:49 +00:00
zhifu gao
74ca876864
Merge pull request #3498 from modelscope/codex/product-site-discovery-metadata-20260817
...
fix(site): publish accurate deployment discovery metadata
2026-08-17 01:49:36 +08:00
LauraGPT
fe92e3a4d1
fix(site): publish deployment discovery metadata
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-16 17:45:54 +00:00
zhifu gao
2e4914e7f9
Merge pull request #3497 from modelscope/codex/site-llamacpp-blog-v020-20260815
...
docs: refresh llama.cpp deployment blog
2026-08-15 03:23:23 +08:00
zhifu gao
534f83ce04
docs: refresh llama.cpp deployment blog
...
Signed-off-by: zhifu gao <[email protected] >
2026-08-14 19:19:11 +00:00
zhifu gao
9041074856
Merge pull request #3494 from wuhongsheng/silero_vad
...
feat(vad): add Silero VAD adapter
2026-08-14 15:39:48 +08:00
LauraGPT
e8ea59a02c
fix(vad): preserve Silero ONNX CPU inputs
2026-08-14 07:35:21 +00:00
LauraGPT
419674e544
fix(vad): keep Silero inputs on the model device
2026-08-14 07:32:23 +00:00
wuhongsheng
22920822a2
feat(vad): add Silero VAD adapter
2026-08-14 11:13:32 +08:00
zhifu gao
79a0ed22e1
Merge pull request #3491 from modelscope/docs/llamacpp-campplus-boundary-20260813
...
docs: clarify llama.cpp speaker diarization support
v1.4.2
2026-08-13 17:43:32 +08:00
zhifu gao
6394ae915e
Merge current main into docs/llamacpp-campplus-boundary-20260813
...
Signed-off-by: zhifu gao <[email protected] >
2026-08-13 09:42:45 +00:00
zhifu gao
3861be24a1
Merge pull request #3492 from modelscope/codex/product-site-vllm-native-20260813
...
docs: validate native FunASR on vLLM 0.27.1
2026-08-13 17:30:07 +08:00
LauraGPT
d1b22baf37
docs: validate native FunASR on vLLM 0.27.1
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-13 09:26:23 +00:00
zhifu gao
65bbd29f60
docs: clarify llama.cpp speaker diarization support
...
Signed-off-by: zhifu gao <[email protected] >
2026-08-13 02:15:55 +00:00
zhifu gao
1dbc9b3ef1
Merge pull request #3490 from modelscope/codex/site-audio-cpp-mainline-20260813
...
docs(site): mark audio.cpp SenseVoice as merged to main
2026-08-13 04:38:46 +08:00
LauraGPT
d1e320c0ca
docs(site): mark audio.cpp SenseVoice as merged to main
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-12 20:34:35 +00:00
zhifu gao
5104ae64fe
Merge pull request #3489 from modelscope/codex/site-sensevoice-native-server-20260813
...
docs(site): add SenseVoice native server deployment
2026-08-13 04:00:22 +08:00
LauraGPT
2469fb73e7
docs(site): add SenseVoice native server deployment
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-12 19:54:57 +00:00
zhifu gao
5c1db4feec
Merge pull request #3488 from modelscope/codex/fix-site-evidence-mobile-overflow-20260813
...
fix(site): prevent mobile evidence overflow
2026-08-13 02:54:32 +08:00
LauraGPT
7c6075a5b8
fix(site): prevent mobile evidence overflow
2026-08-12 18:50:20 +00:00
zhifu gao
72d7bc7221
Merge pull request #3487 from modelscope/codex/site-audio-cpp-sensevoice-20260813
...
docs(site): add SenseVoice audio.cpp deployment
2026-08-13 02:42:13 +08:00
LauraGPT
93e4cbbc3e
docs(site): add SenseVoice audio.cpp deployment
2026-08-12 18:36:37 +00:00
zhifu gao
e7d9c3e0b5
Merge pull request #3485 from modelscope/codex/funasr-1.4.2-release-audit-20260812
...
chore: prepare FunASR 1.4.2 release
2026-08-12 03:23:23 +08:00
LauraGPT
8c08e2636b
chore: prepare FunASR 1.4.2 release
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-11 18:23:20 +00:00
zhifu gao
62b784b2b9
docs: surface llama.cpp runtime v0.2.0 ( #3484 )
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-11 14:17:59 +08:00
zhifu gao
9e983c6c4a
docs(site): publish llama.cpp v0.2.0 downloads ( #3483 )
...
Signed-off-by: zhifu gao <[email protected] >
2026-08-11 13:17:31 +08:00
zhifu gao
500956bc33
fix(vulkan): refresh ggml for AMD submission handling ( #3482 )
...
Refresh the pinned llama.cpp revision with AMD Vulkan submission batching and DeviceLost diagnostics, adapt the sampler API, and document Windows troubleshooting. Refs #3479 .
runtime-llamacpp-v0.2.0
2026-08-11 12:19:11 +08:00
Dingyuan Wang
b0d44bd792
llama.cpp: add srt output ( #3480 )
...
Add optional SRT output to Fun-ASR-Nano, SenseVoiceSmall, and Paraformer llama.cpp runtimes. Preserve existing non-SRT output behavior and document VAD-aligned subtitle generation.
2026-08-11 11:27:36 +08:00
zhifu gao
680b1b3f10
docs(vllm): clarify official model paths ( #3476 )
...
Clarify official and native vLLM model paths. Closes #3475 .
2026-08-05 16:23:20 +08:00
zhifu gao and zhifu gao
ea21a7e53a
test(site): refresh ecosystem contract ( #3474 )
...
Signed-off-by: zhifu gao <[email protected] >
Co-authored-by: zhifu gao <[email protected] >
2026-08-05 15:09:27 +08:00
zhifu gao and zhifu gao
1e6ec0cbe2
docs(site): refresh ecosystem evidence ( #3473 )
...
Signed-off-by: zhifu gao <[email protected] >
Co-authored-by: zhifu gao <[email protected] >
2026-08-05 15:00:44 +08:00
May
112b80fa0b
fix(train): initialize DeepSpeed mode from resolved config ( #3471 )
...
Resolve distributed trainer settings once with top-level precedence and backwards-compatible train_conf fallbacks. Remove consumed mode keys before expanding trainer_conf, reject simultaneous FSDP and DeepSpeed, and cover the behavior with focused tests.
2026-08-05 11:35:53 +08:00
May
d410a5652d
fix(train): align DDP no_sync with gradient accumulation ( #3472 )
...
Synchronize DDP/FSDP gradients on the final microbatch of each accumulation window.
Verified with a two-rank CPU/Gloo reproduction, py_compile, diff checks, and a clean synthetic merge against current main.
2026-08-05 11:32:24 +08:00
zhifu gao
6829ba7845
fix(auto-model): align split punctuation tokens ( #3469 )
...
Preserve subtitle segmentation when punctuation token boundaries split a timestamped ASR word.
Signed-off-by: LauraGPT <[email protected] >
2026-08-04 14:27:55 +08:00
zhifu gao
06c59d2b46
Merge pull request #3467 from modelscope/codex/release-1.4.1-20260804
...
chore: release FunASR 1.4.1
v1.4.1
2026-08-04 10:27:57 +08:00
LauraGPT
7a974018c2
chore: prepare FunASR 1.4.1 release
...
Signed-off-by: LauraGPT <[email protected] >
2026-08-04 02:23:14 +00:00
zhifu gao
187dc73f08
fix: route paraformer-en to the English HF model ( #3466 )
...
Route the Hugging Face paraformer-en alias to the official English checkpoint and keep the behavior covered by a regression test.
2026-08-04 10:06:33 +08:00
zhifu gao and LauraGPT
5405b74e15
feat: add OpenClaw realtime transcription plugin ( #3465 )
...
Co-authored-by: LauraGPT <[email protected] >
2026-08-04 05:53:13 +08:00
zhifu gao and LauraGPT
99879903d2
docs(site): add SenseVoice TensorRT deployment ( #3464 )
...
Co-authored-by: LauraGPT <[email protected] >
2026-08-04 02:46:58 +08:00
zhifu gao and LauraGPT
6408aaa96d
feat(runtime): add SenseVoice TensorRT deployment ( #3463 )
...
Co-authored-by: LauraGPT <[email protected] >
2026-08-04 02:22:57 +08:00
zhifu gao and LauraGPT
4dc8e5b4f0
feat(runtime): add JSONL timestamp output ( #3462 )
...
Signed-off-by: LauraGPT <[email protected] >
Co-authored-by: LauraGPT <[email protected] >
2026-08-04 01:00:20 +08:00