Concedo baacd640c0 Merge commit 'dd1557907ae50e11814e25609b30825b67963663' into concedo_experimental ...

# Conflicts:
#	.github/workflows/build-vulkan.yml
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/test-llama-archs.cpp
#	tools/perplexity/perplexity.cpp
#	tools/server/README.md

2026-05-30 01:40:09 +08:00

..

bench

Merge branch 'upstream' into concedo_experimental

2026-03-22 23:39:13 +08:00

tests

Merge branch 'upstream' into concedo_experimental

2026-05-18 21:27:23 +08:00

chat-llama2.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

chat.mjs

llama : move end-user examples to tools directory (#13249)

2025-05-02 20:27:13 +02:00

chat.sh

scripts : make the shell scripts cross-platform (#14341)

2025-06-30 10:17:18 +02:00

main.cpp

app : introduce the llama unified executable (#23296)

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

README-dev.md

ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064)

2026-05-16 02:02:40 +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: fix checkpoints creation (#22929)

2026-05-25 08:56:18 +03:00

server-common.h

logs : reduce (#23021)

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

server-context.cpp

server: MTP layer kv-cache should respect draft type ctk (#23646)

2026-05-25 16:46:23 +08:00

server-context.h

ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064)

2026-05-16 02:02:40 +02:00

server-cors-proxy.h

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

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

server-http.cpp

server: minor tweaks to use more cpp features (#23785)

2026-05-28 14:00:25 +02:00

server-http.h

server: minor tweaks to use more cpp features (#23785)

2026-05-28 14:00:25 +02:00

server-models.cpp

server: re-inject subcommand when router spawns children under unified binary (#23442)

2026-05-21 10:09:19 +02:00

server-models.h

ui: Restructure repo to use tools/ui folder and ui / UI / llama-ui / LLAMA_UI naming (#23064)

2026-05-16 02:02:40 +02:00

server-queue.cpp

server : print warning when HTTP timeout exceeded (#22907)

2026-05-10 22:00:18 +03:00

server-queue.h

server: allow router to report child instances sleep status (#20849)

2026-03-22 18:33:52 +01:00

server-task.cpp

server: only parse empty msg if continuing an assistant msg (#23506)

2026-05-22 11:58:15 -04:00

server-task.h

server: fix checkpoints creation (#22929)

2026-05-25 08:56:18 +03:00

server-tools.cpp

server : validate --tools CLI argument against known tool names (#22538)

2026-05-05 06:35:27 +03:00

server-tools.h

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

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

server.cpp

app : introduce the llama unified executable (#23296)

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