Commit Graph
5674 Commits
Author SHA1 Message Date
LauraGPT c567595900 feat(runtime): add Windows Blackwell CUDA asset
Signed-off-by: LauraGPT <[email protected]>
2026-08-30 01:48:01 +00:00
zhifu gao 8b55e45334 Merge pull request #3569 from modelscope/codex/moss-localai-site-20260830
docs: expose MOSS LocalAI edge path
2026-08-30 06:53:01 +08:00
LauraGPT 3162ffe1a8 docs: expose MOSS LocalAI edge path
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 22:48:31 +00:00
zhifu gao c944c72a4a Merge pull request #3568 from modelscope/codex/moss-long-audio-contract-20260830
feat(moss): support long vLLM transcriptions
2026-08-30 06:12:36 +08:00
LauraGPT d6ee34ea92 feat(moss): support long vLLM transcriptions
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 22:10:12 +00:00
zhifu gao 81b07bc25e Merge pull request #3567 from modelscope/codex/refresh-roadmap-20260830
docs: refresh repository roadmap and issue boundaries
2026-08-30 03:51:02 +08:00
LauraGPT 93a11f8ba6 docs: refresh repository roadmap and issue boundaries
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 19:48:59 +00:00
zhifu gao 4300a6b2a1 feat(moss): support vLLM diarized responses (#3566)
Signed-off-by: LauraGPT <[email protected]>
2026-08-30 03:25:43 +08:00
LauraGPT 14e154ad2a feat(moss): support vLLM diarized responses
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 19:19:25 +00:00
zhifu gao f0c5b4a149 fix(download): preserve snapshot errors (#3565)
Related to #3523.

Signed-off-by: LauraGPT <[email protected]>
2026-08-30 02:36:45 +08:00
zhifu gao 00dd1a54e0 chore(release): prepare 1.4.7 (#3564)
Signed-off-by: LauraGPT <[email protected]>
v1.4.7
2026-08-30 02:17:26 +08:00
zhifu gao 3c79578040 Merge pull request #3563 from modelscope/codex/moss-automodel-20260830
docs(moss): sync AutoModel deployment matrices
2026-08-30 02:00:03 +08:00
LauraGPT b64f1d617e docs(moss): sync AutoModel deployment matrices
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 17:58:31 +00:00
zhifu gao 84eea83a26 Merge pull request #3561 from modelscope/codex/realtime-l20-profile-20260830
perf(realtime): add opt-in decode profiling
2026-08-30 01:25:27 +08:00
LauraGPT 4bccc3a091 perf(realtime): add opt-in decode profiling
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 17:23:30 +00:00
zhifu gao 3afdf7b2c9 Merge pull request #3562 from modelscope/codex/fix-srt-tiny-gap-boundary-20260830
Fix tiny-gap semantic boundaries in readable SRT
2026-08-30 01:17:55 +08:00
LauraGPT db959d3010 fix(cli): repack tiny-gap subtitle boundaries
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 17:15:20 +00:00
zhifu gao ffa7b29bc6 Merge pull request #3560 from modelscope/codex/runtime-v023-links-20260830
test(release): track current llama.cpp runtime
2026-08-30 00:49:58 +08:00
LauraGPT b8bd680578 test(release): track current llama.cpp runtime
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 16:48:59 +00:00
zhifu gao 925e6cbd28 Merge pull request #3559 from modelscope/codex/site-moss-automodel-20260830
docs(moss): expose AutoModel deployment contract
2026-08-30 00:15:59 +08:00
LauraGPT db2639d47c docs(moss): expose AutoModel deployment contract
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 16:10:20 +00:00
zhifu gao a3a2de0aed Merge pull request #3558 from modelscope/codex/moss-runtime-integration
feat(moss): add AutoModel runtime adapter
2026-08-29 23:59:48 +08:00
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
LauraGPT 9fc7b30cab feat(moss): add AutoModel runtime adapter
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 15:53:24 +00:00
zhifu gao 7e3e249534 Merge pull request #3557 from modelscope/codex/site-runtime-v025-20260829
docs(runtime): publish verified v0.2.5 download matrix
2026-08-29 23:15:00 +08:00
LauraGPT 36f03086af docs(runtime): publish verified v0.2.5 download matrix
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 15:02:09 +00:00
zhifu gao 9f0d4834e5 Merge pull request #3556 from LauraGPT/codex/moss-transcribe-diarize-ecosystem
docs(ecosystem): add MOSS diarization deployment path
2026-08-29 22:22:47 +08:00
LauraGPT 73410e6866 docs(ecosystem): add MOSS diarization deployment path
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 14:10:07 +00:00
zhifu gao f371370d4c Merge pull request #3555 from modelscope/codex/fix-vulkan-weight-buffer-3479
fix(runtime): upload SenseVoice weights to selected backend
runtime-llamacpp-v0.2.5
2026-08-29 22:05:42 +08:00
LauraGPT 949ccf46f3 fix(runtime): upload SenseVoice weights to backend buffer
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 13:26:37 +00:00
zhifu gao fcf9a0d4a6 Merge pull request #3552 from modelscope/codex/runtime-v024-site
docs(site): publish llama.cpp v0.2.4 evidence
2026-08-29 15:53:14 +08:00
LauraGPT be79f1e074 docs(site): publish llama.cpp v0.2.4 evidence
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 07:49:00 +00:00
zhifu gao c8d43b10de Merge pull request #3551 from modelscope/codex/runtime-v024-prepare
docs(runtime): prepare llama.cpp v0.2.4 release
runtime-llamacpp-v0.2.4
2026-08-29 11:26:38 +08:00
LauraGPT d15175f361 docs(runtime): prepare llama.cpp v0.2.4 release
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 03:25:09 +00:00
zhifu gao f04b761f51 Merge pull request #3550 from modelscope/codex/fix-sensevoice-empty-output
fix(runtime): decode SenseVoice F16 query embeddings
2026-08-29 11:18:25 +08:00
LauraGPT 178a36718c fix(runtime): decode SenseVoice F16 query embeddings
Signed-off-by: LauraGPT <[email protected]>
2026-08-29 02:40:29 +00:00
zhifu gao 159f67b154 chore(release): prepare 1.4.6 (#3549)
Publish the realtime keepalive, empty timestamp segment, and readable subtitle fixes with the verified llama.cpp v0.2.3 nine-platform runtime matrix.

Signed-off-by: LauraGPT <[email protected]>
v1.4.6
2026-08-29 09:23:49 +08:00
zhifu gao baea5672cc Merge pull request #3548 from modelscope/codex/runtime-v023-site
docs(site): publish llama.cpp runtime v0.2.3 matrix
2026-08-29 02:42:15 +08:00
LauraGPT 872543e49b docs(site): publish llama.cpp runtime v0.2.3 matrix
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 18:38:00 +00:00
zhifu gao 820f1c64a3 Merge pull request #3547 from LauraGPT/codex/runtime-v023-docs
docs(runtime): publish v0.2.3 diagnostics
runtime-llamacpp-v0.2.3
2026-08-29 01:59:36 +08:00
LauraGPT cabecbf133 test(runtime): track v0.2.3 release contract
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 17:58:13 +00:00
LauraGPT 6ded40886c docs(runtime): publish v0.2.3 diagnostics
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 17:55:23 +00:00
zhifu gao 0786ccce16 Merge pull request #3546 from LauraGPT/codex/runtime-amd-boundaries-3479
fix(runtime): trace SenseVoice backend stages
2026-08-29 01:52:08 +08:00
LauraGPT 7429dbd787 fix(runtime): trace SenseVoice backend stages
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 17:14:09 +00:00
zhifu gao 588cabd79c Merge pull request #3545 from modelscope/codex/site-runtime-v022-product-20260829
Update product site for llama.cpp v0.2.2
2026-08-29 00:17:08 +08:00
LauraGPT 3575c03b11 Update product site for llama.cpp v0.2.2
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 16:08:52 +00:00
zhifu gao 05be4863fc Merge pull request #3543 from LauraGPT/codex/amd-vulkan-init-3479
fix(vulkan): guard backend initialization failures
runtime-llamacpp-v0.2.2
2026-08-28 22:51:15 +08:00
LauraGPT 0395c59eb7 fix(vulkan): guard backend initialization failures
Signed-off-by: LauraGPT <[email protected]>
2026-08-28 14:49:31 +00:00
zhifu gao 45cb6743fc Merge pull request #3533 from LauraGPT/codex/realtime-ws-keepalive-3528
fix(realtime): avoid false keepalive timeouts under load
2026-08-28 22:34:50 +08:00