1.14 GB

Ctrl+K

1 contributor

History: 36 commits

jfan

Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared

1795933 verified 42 minutes ago

packages
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
wasm
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
wasm_vision_hires
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
.gitattributes

1.52 kB
initial commit 12 days ago
README.md

713 Bytes
Release WebGPU WASM runtime & @litert-lm/core v0.17.10-dev (unified cross-backend MTP & multimodal WebGPU runtime) 5 days ago
litert-lm-core-0.17.10-dev.tgz

35.8 MB
xet

Release WebGPU WASM runtime & @litert-lm/core v0.17.10-dev (unified cross-backend MTP & multimodal WebGPU runtime) 5 days ago
litert-lm-core-0.17.10.tgz

35.5 MB
xet

Release WebGPU WASM runtime & @litert-lm/core v0.17.10 (V100 WebGPU MTP & vision optimizations, live tool streaming, browser RGBA8 decode) 7 days ago
litert-lm-core-0.17.8-dev.tgz

35.5 MB
xet

Update 0.17.8-dev tgz and -c opt WASM with MTP probability_cache and token_override fixes 12 days ago
litert-lm-core-0.17.9-dev.tgz

35.5 MB
xet

Release LiteRT-LM Web Runtime 0.17.9-dev (clean 111-entry tarball + latest -c opt WASM) 8 days ago
litert-lm-core-0.18.0-dev.tgz

36.3 MB
xet

Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litert-lm-core-0.18.0.tgz

36.3 MB
xet

Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litert-lm-core-0.18.1-dev.tgz

35.2 MB
xet

Publish @litert-lm/core@0.18.1-dev ESM clean tsc build (fix goog is not defined) 1 day ago
litertlm_wasm_asyncify_internal.aw.js

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.d.ts

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.data

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.html

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.js

303 kB
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litertlm_wasm_asyncify_internal.js.symbols

5.21 MB
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_asyncify_internal.symbols

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.wasm

36.8 MB
xet

Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litertlm_wasm_asyncify_internal.wasm.debug.wasm

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.wasm.js.symbols

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.wasm.map

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.wasm.orig

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal.wasm.runfiles_manifest

376 Bytes
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_asyncify_internal.ww.js

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_asyncify_internal_nodata.js

311 kB
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_asyncify_internal_preloaded.data

0 Bytes
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_compat_asyncify_internal.aw.js

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.d.ts

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.data

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.html

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.js

303 kB
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litertlm_wasm_compat_asyncify_internal.js.symbols

5.21 MB
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_compat_asyncify_internal.symbols

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.wasm

36.6 MB
xet

Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litertlm_wasm_compat_asyncify_internal.wasm.debug.wasm

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.wasm.js.symbols

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.wasm.map

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.wasm.orig

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal.wasm.runfiles_manifest

404 Bytes
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_compat_asyncify_internal.ww.js

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_asyncify_internal_nodata.js

311 kB
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_compat_asyncify_internal_preloaded.data

0 Bytes
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago
litertlm_wasm_compat_internal.aw.js

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_internal.d.ts

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_internal.data

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_internal.html

0 Bytes
Fix LockedLlmExecutor speculative metrics forwarding and per-turn BenchmarkInfo telemetry 11 days ago
litertlm_wasm_compat_internal.js

295 kB
Fix MTP shared KV scale cache retention across streaming LlmWebGpu::Init -> InitShared 42 minutes ago
litertlm_wasm_compat_internal.js.symbols

5.21 MB
Build latest WebGPU WASM runtime & @litert-lm/core (DraftTokens drafter_pos KV slot fix + Leviathan rejection sampling + top-p WGSL + media_cache_size_) 8 days ago