Concedo 5b54b90dca Merge branch 'upstream' into concedo_experimental ...

# Conflicts:
#	ci/run.sh
#	docs/backend/SYCL.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	examples/sycl/start-svr.sh
#	examples/sycl/test.sh
#	examples/sycl/win-start-svr.bat
#	examples/sycl/win-test.bat
#	ggml/CMakeLists.txt
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/fattn-vec.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/presets.hpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-sycl/ssm_conv.cpp
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
#	tests/test-model-resolution.cpp
#	tests/test-mtmd-c-api.c

2026-08-08 17:08:22 +08:00

..

bench

Merge branch 'upstream' into concedo_experimental

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

tests

Merge branch 'upstream' into concedo_experimental

2026-08-08 17:08:22 +08:00

main.cpp

app : introduce the llama unified executable (#23296)

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

README-dev.md

server: (tools) add x-tool-cwd header (#26420)

2026-08-03 10:47:21 +02:00

server-chat.cpp

server: support "reasoning_effort": "none" in OAI API (#26045)

2026-07-24 19:19:10 +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

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

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

server-common.h

server: support MCP stdio (#26062)

2026-07-26 01:08:49 +02:00

server-context.cpp

server: Adding spec-decode counters to /metrics endpoint (#26389)

2026-08-05 12:36:01 +02:00

server-context.h

llama : add llama_model_ftype_name() (#25134)

2026-07-02 17:26:47 +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

server: Ignore empty / non-existing Origin headers (#25756)

2026-07-16 12:26:51 +03:00

server-http.h

server: refactor server_stream (#25541)

2026-07-11 12:41:47 +02:00

server-mcp.cpp

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

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

server-mcp.h

server: support MCP stdio (#26062)

2026-07-26 01:08:49 +02:00

server-models.cpp

server: (router) add LRU scheduler (#26572)

2026-08-07 14:46:53 +02:00

server-models.h

server: (router) add LRU scheduler (#26572)

2026-08-07 14:46:53 +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

server : clarify comment in eval_llama_cmpl_schema [no ci] [no release] (#26720)

2026-08-07 15:39:33 +02:00

server-schema.h

sampler : remove "full-context windows" from history-based samplers (#26524)

2026-08-04 21:28:55 +03:00

server-stream.cpp

server + ui: fix stream routes for model names containing a slash (#26137)

2026-07-27 07:34:47 +02:00

server-stream.h

server + ui: fix stream routes for model names containing a slash (#26137)

2026-07-27 07:34:47 +02:00

server-task.cpp

server: Adding spec-decode counters to /metrics endpoint (#26389)

2026-08-05 12:36:01 +02:00

server-task.h

server: Adding spec-decode counters to /metrics endpoint (#26389)

2026-08-05 12:36:01 +02:00

server-tools.cpp

server: harden the file_glob_search directory walk (#26626)

2026-08-05 21:31:54 +02:00

server-tools.h

server: support MCP stdio (#26062)

2026-07-26 01:08:49 +02:00

server.cpp

server: add notice for upcoming default port change 8080 --> 9931 (#26508)

2026-08-03 12:45:24 +02:00

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