-
Notifications
You must be signed in to change notification settings - Fork 34
All issues
Issue creation is restricted in this repository
Issues
is:issue state:open
is:issue state:open
Search results
epic: Multi-turn prompt cache never hits for snapshot-only families (Gemma 4, Qwen 3.5, SSM hybrids)
area:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)priority:highHigh priorityHigh prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1148 In lablup/mlxcel;feat: Classify snapshot-divergence rejects in prompt-cache stats
area:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)priority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1147 In lablup/mlxcel;feat: Snapshot capacity hygiene: session-chain supersede and configurable budget
area:cliCommand-line interface / CLI flagsCommand-line interface / CLI flagsarea:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)priority:highHigh priorityHigh prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1146 In lablup/mlxcel;feat: Partial snapshot restore at the longest common prefix for unwrapped rotating layers (rotating-attention families only)
area:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)area:modelsModel architectures, weights, loading, metadataModel architectures, weights, loading, metadatapriority:mediumMedium priorityMedium prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1145 In lablup/mlxcel;feat: Post-completion incremental warm-up snapshot for the next turn's history prefix
area:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)priority:mediumMedium priorityMedium prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1144 In lablup/mlxcel;feat: Donate a history-boundary snapshot during prefill for snapshot-only families
area:inferenceGeneration, sampling, decoding (incl. speculative, DRY)Generation, sampling, decoding (incl. speculative, DRY)priority:highHigh priorityHigh prioritystatus:readyReady to be worked onReady to be worked ontype:enhancementNew features, capabilities, or significant additionsNew features, capabilities, or significant additionsStatus: Open.#1143 In lablup/mlxcel;chore: Enforce the
// Used by:convention in CI, staleness includedpriority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:choreMaintenance tasks (build, CI, etc.)Maintenance tasks (build, CI, etc.)Status: Open.#1141 In lablup/mlxcel;chore: Add a CI check keeping environment-variables.md in sync with src
priority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:choreMaintenance tasks (build, CI, etc.)Maintenance tasks (build, CI, etc.)Status: Open.#1140 In lablup/mlxcel;docs: Correct the stale "not a server knob" claim in docs/turbo-kv-cache.md
priority:mediumMedium priorityMedium prioritystatus:readyReady to be worked onReady to be worked ontype:docsDocumentation improvements or additionsDocumentation improvements or additionsStatus: Open.#1139 In lablup/mlxcel;chore(build): guard
webpage-buildagainst the missing MkDocs manual sourcespriority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:choreMaintenance tasks (build, CI, etc.)Maintenance tasks (build, CI, etc.)Status: Open.#1138 In lablup/mlxcel;fix: Unparseable MLXCEL_PAGED_SLAB_BLOCKS warns about a derived size it never uses
priority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:bugBug fixes, error corrections, or issue resolutionsBug fixes, error corrections, or issue resolutionsStatus: Open.#1137 In lablup/mlxcel;fix(cli): unreachable 2D-parallelism guard in validate_pipeline_parallel_args, decide whether to delete it or widen the early return
priority:lowLow priorityLow prioritystatus:readyReady to be worked onReady to be worked ontype:bugBug fixes, error corrections, or issue resolutionsBug fixes, error corrections, or issue resolutionsStatus: Open.#1131 In lablup/mlxcel;