王金旭 662a0b0121 spec : fuse the DFlash encoder into the KV cache injection (#27310) ...

* dflash : fuse the encoder into the KV injection decode

The encoder is a single fc + norm, but running it as a separate
llama_encode forced a device-to-host round trip of its output before the
injection decode could re-upload it, plus a second graph build per
round. Fold the encoder into the decoder's embd branch and feed the
target features directly to one llama_decode.

Assisted-by: Claude Fable

* nit

* Apply batched suggestions from code review

Co-authored-by: Ruixiang Wang <wangruixiang07@outlook.com>

* Fix missing references from renaming

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Ruixiang Wang <wangruixiang07@outlook.com>

2026-08-31 11:19:20 +02:00

..

jinja

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

arg.cpp

common: rename --tensor-read-lazy to --lazy-mode, add -lzm shorthand (#27969)

2026-08-30 09:18:10 +03:00

arg.h

server: add dedup-cache-models preset option (#27346)

2026-08-19 11:04:26 +02:00

base64.hpp

llava : expose as a shared library for downstream projects (#3613)

2023-11-07 00:36:23 +03:00

build-info.cpp.in

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

build-info.h

cmake : introduce semantic versioning (#26839)

2026-08-12 14:15:03 +02:00

chat-auto-parser-generator.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat-auto-parser-helpers.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat-auto-parser-helpers.h

chat : avoid including json in chat.h (#21306)

2026-04-03 09:07:59 +03:00

chat-auto-parser.h

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat-diff-analyzer.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat-peg-parser.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat-peg-parser.h

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

chat.cpp

chat : scope qwen3-coder workarounds (#27679)

2026-08-25 09:33:00 -05:00

chat.h

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

CMakeLists.txt

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

common.cpp

bench: add --tensor-read-lazy (#27881)

2026-08-28 20:51:05 +02:00

common.h

bench: add --tensor-read-lazy (#27881)

2026-08-28 20:51:05 +02:00

console.cpp

cli: fix stripping of \n in multiline input (#21485)

2026-04-06 20:54:06 +02:00

console.h

cli : add command and file auto-completion (#19985)

2026-03-05 10:47:28 +01:00

debug.cpp

common: fix missing exports in llama-common (#22340)

2026-04-27 08:06:39 +03:00

debug.h

common: fix missing exports in llama-common (#22340)

2026-04-27 08:06:39 +03:00

download.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

download.h

server: add dedup-cache-models preset option (#27346)

2026-08-19 11:04:26 +02:00

fit.cpp

fit: also take into account n_streams (#27496)

2026-08-22 16:16:06 +02:00

fit.h

fit: also take into account n_streams (#27496)

2026-08-22 16:16:06 +02:00

hf-cache.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

hf-cache.h

server: (router) add model management API (#23976)

2026-06-17 18:04:58 +02:00

http.h

cli : move to HTTP-based implementation (#24948)

2026-07-08 14:52:43 +02:00

imatrix-loader.cpp

fix: check gguf array type before reading (#27075)

2026-08-15 11:45:30 +02:00

imatrix-loader.h

Move duplicated imatrix code into single common imatrix-loader.cpp (#22445)

2026-06-04 17:45:40 +02:00

json-schema-to-grammar.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

json-schema-to-grammar.h

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

json.cpp

common: json.h: fix clang lto (#27575)

2026-08-23 01:11:10 +02:00

json.h

common: json.h: fix clang lto (#27575)

2026-08-23 01:11:10 +02:00

llguidance.cpp

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

log.cpp

common: update logging to enforce max_capacity and optimize queue resizing (#24490)

2026-06-17 09:19:11 +03:00

log.h

logs : reduce (#23021)

2026-05-14 13:05:52 +03:00

ngram-cache.cpp

spec : add self‑speculative decoding (no draft model required) + refactor (#18471)

2026-01-28 19:42:42 +02:00

ngram-cache.h

spec : add self‑speculative decoding (no draft model required) + refactor (#18471)

2026-01-28 19:42:42 +02:00

ngram-map.cpp

speculative : fix out-of-bounds read in ngram-map on prompt shrink (#23936)

2026-07-07 10:25:04 +03:00

ngram-map.h

fix: correct misspellings in code comments (#21217)

2026-03-31 13:50:51 +02:00

ngram-mod.cpp

ngram-mod : Add missing include (#23857)

2026-05-29 09:21:37 +03:00

ngram-mod.h

ngram-mod : fix build [no ci] (#19216)

2026-01-30 21:27:27 +02:00

peg-parser.cpp

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

peg-parser.h

common: add json.h abstraction (#27511)

2026-08-22 16:28:28 +02:00

preset.cpp

common: support --models-dir loading MTP assistant models (#24431)

2026-08-15 13:17:35 +02:00

preset.h

common: add system-level config file (#26118)

2026-08-13 00:02:27 +02:00

reasoning-budget.cpp

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

reasoning-budget.h

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

2026-07-25 11:58:09 +02:00

sampling.cpp

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

sampling.h

llama : support multi-output backend sampling (#25532)

2026-08-10 16:58:56 +03:00

speculative.cpp

spec : fuse the DFlash encoder into the KV cache injection (#27310)

2026-08-31 11:19:20 +02:00

speculative.h

spec: Add benchmark-only synthetic speculative acceptance options (#27711)

2026-08-27 13:53:42 +03:00

subproc.cpp

common: add subproc.h wrapper, disabled on android/ios (#26102)

2026-07-26 20:54:25 +02:00

subproc.h

common: add subproc.h wrapper, disabled on android/ios (#26102)

2026-07-26 20:54:25 +02:00

trie.cpp

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

2026-07-25 11:58:09 +02:00

trie.h

common : add support for multiple end sequences in the reasoning budget sampler (#25544)

2026-07-25 11:58:09 +02:00

unicode.cpp

common/parser: handle reasoning budget (#20297)

2026-03-11 10:26:12 +01:00

unicode.h

common/parser: handle reasoning budget (#20297)

2026-03-11 10:26:12 +01:00