Concedo 56d11ad4e8 Merge branch 'upstream' into concedo_experimental ...

# Conflicts:
#	docs/backend/OPENCL.md
#	ggml/src/ggml-hexagon/CMakeLists.txt
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hex-dma.h
#	ggml/src/ggml-hexagon/htp/hmx-utils.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/hvx-base.h
#	ggml/src/ggml-hexagon/htp/hvx-exp.h
#	ggml/src/ggml-hexagon/htp/hvx-sigmoid.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-tool.sh
#	scripts/snapdragon/ggml-hexagon-profile.py
#	tests/test-backend-ops.cpp

2026-07-02 21:42:36 +08:00

..

bench

Merge branch 'upstream' into concedo_experimental

2026-06-16 17:55:04 +08:00

tests

Merge commit '9d5d882d8cd0f0a9283d87ed5e6fe3ee0d925fb1' into concedo_experimental

2026-06-27 10:18:52 +08:00

main.cpp

app : introduce the llama unified executable (#23296)

2026-05-20 13:22:22 +02:00

README-dev.md

server + ui: SSE Replay Buffer (#23226)

2026-06-26 09:31:29 +02:00

server-chat.cpp

Support for Codex CLI by skipping unsupported Responses tools (#23041)

2026-05-15 09:03:24 +02:00

server-chat.h

server: (router) Forward form-data to model server (Fixes #22044) (#22118)

2026-04-27 23:55:00 +02:00

server-common.cpp

server: improve user message detection and create checkpoints at every user message (#24176)

2026-06-23 08:27:28 +03:00

server-common.h

server: improve user message detection and create checkpoints at every user message (#24176)

2026-06-23 08:27:28 +03:00

server-context.cpp

jinja, chat: add --reasoning-preserve flag (#25105)

2026-06-28 23:33:51 +02:00

server-context.h

server: (router) move model downloading to dedicated process (#24834)

2026-06-22 18:24:04 +02:00

server-cors-proxy.h

common,server: handle bracketed IPv6 literals in URL authority (#25140)

2026-06-30 16:16:44 +02:00

server-http.cpp

common,server: handle bracketed IPv6 literals in URL authority (#25140)

2026-06-30 16:16:44 +02:00

server-http.h

server + ui: SSE Replay Buffer (#23226)

2026-06-26 09:31:29 +02:00

server-models.cpp

common,server: handle bracketed IPv6 literals in URL authority (#25140)

2026-06-30 16:16:44 +02:00

server-models.h

server + ui: SSE Replay Buffer (#23226)

2026-06-26 09:31:29 +02:00

server-queue.cpp

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

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

server-queue.h

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

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

server-schema.cpp

logs : reduce v2 (#25078)

2026-06-28 08:52:15 +03:00

server-schema.h

server: add "schema" and validation (#24150)

2026-06-18 15:40:58 +02:00

server-stream.cpp

ui: fix stop and reasoning skip in single-model mode (#25084)

2026-06-28 21:06:43 +02:00

server-stream.h

server + ui: SSE Replay Buffer (#23226)

2026-06-26 09:31:29 +02:00

server-task.cpp

logs : reduce v2 (#25078)

2026-06-28 08:52:15 +03:00

server-task.h

server: improve user message detection and create checkpoints at every user message (#24176)

2026-06-23 08:27:28 +03:00

server-tools.cpp

server: fix edit_file crash on append at end of file (line_start -1) (#24893)

2026-06-22 10:55:28 +02:00

server-tools.h

server: add built-in tools backend support (#20898)

2026-03-27 10:07:11 +01:00

server.cpp

logs : reduce v2 (#25078)

2026-06-28 08:52:15 +03:00

ui.cpp

can build llama server now

2026-06-14 15:06:37 +08:00

ui.h

can build llama server now

2026-06-14 15:06:37 +08:00