llama.cpp/tools
Pascal e7140051b7 webui: incremental MDAST transform caching for streaming performance
Replace full AST re-transformation with per-block caching strategy.
Previously, each streaming chunk triggered processor.run() on the entire
document (12 rehype/remark plugins including KaTeX and highlight.js).

Now transforms individual MDAST nodes and caches results by position hash.
In append-only streaming mode, stable blocks are reused directly from cache,
only the unstable trailing block is re-transformed.

- Add SvelteMap FIFO cache (5000 blocks, evicts oldest 1000 on overflow)
- Add getMdastNodeHash() for MDAST node fingerprinting by position
- Add isAppendMode() to detect streaming append patterns
- Add transformMdastNode() for single-node transformation with cache lookup
- Remove stringifyProcessedNode() (dead code after refactor)

Reduces streaming complexity from O(N × transforms) to O(1) for stable blocks.
Targets 200K token contexts without UI degradation on mobile devices.
2026-02-13 14:00:06 +01:00
..
batched-bench tool/ex/tests: consistently free ctx, then model (#18168) 2025-12-22 11:00:37 +01:00
cli support --verbose-prompt (#19576) 2026-02-13 12:49:10 +01:00
completion completion : simplify batch (embd) processing (#19286) 2026-02-04 05:43:28 +01:00
cvector-generator docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
export-lora docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
fit-params llama-fit-params: keep explicit --ctx-size 0 (#19070) 2026-01-24 22:13:08 +01:00
gguf-split cli: new CLI experience (#17824) 2025-12-10 15:28:59 +01:00
imatrix common : refactor common_sampler + grammar logic changes (#17937) 2025-12-14 10:11:13 +02:00
llama-bench Setting mmap and direct_io to false as default in llama-bench.cpp (#18841) 2026-01-16 09:46:51 +01:00
mtmd model: Add Kimi-K2.5 support (#19170) 2026-02-11 16:47:30 +01:00
perplexity docs : Minor cleanups (#19252) 2026-02-02 08:38:55 +02:00
quantize llama-quantize : cleanup `--help` output (#19317) 2026-02-08 09:22:38 +02:00
rpc rpc : update from common.cpp (#19400) 2026-02-08 09:06:45 +01:00
server webui: incremental MDAST transform caching for streaming performance 2026-02-13 14:00:06 +01:00
tokenize cmake : Do not install tools on iOS targets (#15903) 2025-09-16 09:54:44 +07:00
tts model : fix wavtokenizer embedding notions (#19479) 2026-02-11 07:52:20 +02:00
CMakeLists.txt cmake: only build cli when server is enabled (#18670) 2026-01-09 16:43:26 +01:00