sglang

allocator

[PD] Support --enable-unified-memory with PD disaggregation (kimi-linear MLA hybrid-Mamba) (#33362 )

2026-08-10 16:07:58 -07:00

buffer_mode

[HiCache] Buffer-only mode for HiCache host memory layer (#34798 )

2026-08-18 19:21:24 -07:00

cpp_radix_tree

[Kernel] Move sgl-kernel under sglang.kernels.aot (#32648 )

2026-07-29 17:25:00 +08:00

cpp_utils

[HiCache] Optimize HiCache hash generation with bulk token byte conversion (#28287 )

2026-07-01 15:44:23 +08:00

hybrid_cache

[HiCache] Support DCP with DSpark (#35221 )

2026-08-19 01:42:19 -07:00

layout

[unified-memory] Support MLA-hybrid-Mamba (Kimi-Linear) on the Triton backend (#32971 )

2026-07-30 22:10:34 -07:00

pool_host

[HiCache] Split the host-memory budget across co-located ranks (#35540 )

2026-08-19 13:01:58 -07:00

sparsity

hisparse: support NIXL DRAM KV destinations for HiSparse (#27563 )

2026-06-27 22:32:29 +08:00

storage

[HiCache] Buffer-only mode for HiCache host memory layer (#34798 )

2026-08-18 19:21:24 -07:00

unified_cache

[UnifiedTree] feat: support runtime attach/detach (#35269 )

2026-08-19 22:49:08 +08:00

allocation_sizing.py

[Fix] Scale the req_to_token row headroom by attn_dcp_size (#35424 )

2026-08-19 00:37:26 -07:00

allocation.py

[NPU] Support DeepSeek-V4 DSpark and refactor DSV4 cache management (#33676 )

2026-08-17 16:27:44 +08:00

base_prefix_cache.py

Refactor kv cache event mixin into a recorder (#35164 )

2026-08-19 01:20:17 +08:00

base_swa_memory_pool.py

Unify full→SWA index translation in init_forward_metadata; drop pool caches (#27091 )

2026-06-03 16:12:27 -07:00

cache_init_params.py

[HiCache] Support packed and sidecar draft caches for MTP/EAGLE/DSpark (#30393 )

2026-08-06 14:31:11 +08:00

chunk_cache.py

[Fix] Respect cache_protected_len in ChunkCache and disabled-radix release paths (#31662 )

2026-07-18 12:04:25 -07:00

common.py

[PD] Preserve decode KV across retraction in HiCache (#34801 )

2026-08-17 08:49:11 -07:00

deepseek_v4_compress_state.py

[NPU] Support DeepSeek-V4 DSpark and refactor DSV4 cache management (#33676 )

2026-08-17 16:27:44 +08:00

deepseek_v4_memory_pool.py

[DSV4] Fix silent KV corruption when speculative draft tokens > 4 (#34189 )

2026-08-09 15:54:41 -07:00

dsa_cache_layer_split.py

[DSA] Skip indexer KV cache for skip-topk layers (#30531 )

2026-08-17 02:02:23 -07:00

embedding_cache_controller.py

[EPD] Batch embedding cache host-device range copies (#31574 )

2026-08-14 22:01:12 +08:00

embedding_store.py

[FEAT] Decouple multimodal global cache from Mooncake (#30392 )

2026-08-10 19:23:19 +08:00

events.py

Refactor kv cache event mixin into a recorder (#35164 )

2026-08-19 01:20:17 +08:00

evict_policy.py

[lint] Enable Ruff UP037 to drop redundant quoted annotations (#27984 )

2026-06-11 17:38:05 -07:00

flush_cache.py

…

hicache_storage.py

[HiCache] Support packed and sidecar draft caches for MTP/EAGLE/DSpark (#30393 )

2026-08-06 14:31:11 +08:00

hiradix_cache.py

[HiCache] Buffer-only mode for HiCache host memory layer (#34798 )

2026-08-18 19:21:24 -07:00

hisparse_memory_pool.py

[mem_cache][3/N] refactor: move HiSparse allocators to allocator/hisparse.py (#26678 )

2026-06-11 19:50:24 +08:00

index_key_cache.py

[DSA] Skip indexer KV cache for skip-topk layers (#30531 )

2026-08-17 02:02:23 -07:00

kv_cache_builder.py

[HiCache] Support DCP with DSpark (#35221 )

2026-08-19 01:42:19 -07:00

kv_cache_configurator.py

spec: size the speculative buffers from the bags, not the startup record (#35024 )

2026-08-17 16:16:56 -07:00

kv_cache_dtype.py

[Feature] Add Muse Glimmer model support (#34262 )

2026-08-11 15:41:52 -07:00

kv_vmm_backing.py

[Memory] Borrow CUDA graph pool storage for EAGLE sampling (#35375 )

2026-08-18 16:19:41 -07:00

l2_transfer.py

refactor(hicache): flatten L2 transfer execution (#34793 )

2026-08-16 00:33:34 -07:00

mamba_checkpoint_pool.py

Remove the HiMambaRadixTree that is no longer in use (#33468 )

2026-08-07 23:01:40 +08:00

mamba_radix_cache.py

Refactor kv cache event mixin into a recorder (#35164 )

2026-08-19 01:20:17 +08:00

mamba_slot_fused.py

Add Inkling model support (#31681 )

2026-07-19 22:57:37 -07:00

memory_pool_host.py

[HiCache] Split the host-memory budget across co-located ranks (#35540 )

2026-08-19 13:01:58 -07:00

memory_pool.py

[DSA] Skip indexer KV cache for skip-topk layers (#30531 )

2026-08-17 02:02:23 -07:00

multi_ended_allocator.py

[PD] Support --enable-unified-memory with PD disaggregation (kimi-linear MLA hybrid-Mamba) (#33362 )

2026-08-10 16:07:58 -07:00

multimodal_cache.py

[VLM] Chunk-aware ViT encoding with per-image cache and lazy device transfer (#22038 )

2026-04-04 16:55:17 +08:00

pure_swa_radix_cache.py

feat: add cache salt support to KV cache events (#30827 )

2026-08-12 16:14:04 -07:00

radix_cache_cpp.py

feat: add cache salt support to KV cache events (#30827 )

2026-08-12 16:14:04 -07:00

radix_cache.py

Refactor kv cache event mixin into a recorder (#35164 )

2026-08-19 01:20:17 +08:00

registry.py

[HiCache] Simple style change for buffer mode (#35574 )

2026-08-19 15:23:21 -07:00

swa_memory_pool.py

Clarify post-capture KV reservation logs (#33598 )

2026-08-04 15:06:11 -07:00

swa_radix_cache.py

Refactor kv cache event mixin into a recorder (#35164 )

2026-08-19 01:20:17 +08:00

unified_memory_pool.py

[PD] Support --enable-unified-memory with PD disaggregation (kimi-linear MLA hybrid-Mamba) (#33362 )

2026-08-10 16:07:58 -07:00

unified_radix_cache.py

[UnifiedTree] feat: support runtime attach/detach (#35269 )

2026-08-19 22:49:08 +08:00

utils.py

feat: add cache salt support to KV cache events (#30827 )

2026-08-12 16:14:04 -07:00