Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit '52e5f0a5c180248ffae41fe74060d21a07651a93' into concedo_experimental

Browse Source 
# Conflicts:
#	examples/gen-docs/gen-docs.cpp
#	examples/lookup/lookup-create.cpp
#	examples/lookup/lookup-stats.cpp
#	examples/lookup/lookup.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/binary.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/rms_norm_mul.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-reasoning-budget.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/rpc-server.cpp
#	tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte
#	tools/server/webui/src/lib/components/app/chat/ChatSidebar/ChatSidebar.svelte
#	tools/server/webui/src/routes/(chat)/+page.svelte
This commit is contained in:
Concedo
2026-04-29 22:27:36 +08:00
parent 07b928386a 52e5f0a5c1
commit 45f8ff49bb
160 changed files with 12167 additions and 8718 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/tests/utils.py
+6 -9
View File
@@ -83,15 +83,14 @@ class ServerProcess:
kv_unified: bool | None = False
server_slots: bool | None = False
pooling: str | None = None
draft: int | None = None
api_key: str | None = None
models_dir: str | None = None
models_max: int | None = None
no_models_autoload: bool | None = None
lora_files: List[str] | None = None
enable_ctx_shift: int | None = False
draft_min: int | None = None
draft_max: int | None = None
spec_draft_n_min: int | None = None
spec_draft_n_max: int | None = None
no_webui: bool | None = None
jinja: bool | None = None
reasoning_format: Literal['deepseek', 'none', 'nothink'] | None = None
@@ -165,8 +164,6 @@ class ServerProcess:
server_args.extend(["--threads", self.n_threads])
if self.n_gpu_layer:
server_args.extend(["--n-gpu-layers", self.n_gpu_layer])
if self.draft is not None:
server_args.extend(["--draft", self.draft])
if self.server_continuous_batching:
server_args.append("--cont-batching")
if self.server_embeddings:
@@ -214,10 +211,10 @@ class ServerProcess:
server_args.append("--context-shift")
if self.api_key:
server_args.extend(["--api-key", self.api_key])
if self.draft_max:
server_args.extend(["--draft-max", self.draft_max])
if self.draft_min:
server_args.extend(["--draft-min", self.draft_min])
if self.spec_draft_n_max:
server_args.extend(["--spec-draft-n-max", self.spec_draft_n_max])
if self.spec_draft_n_min:
server_args.extend(["--spec-draft-n-min", self.spec_draft_n_min])
if self.no_webui:
server_args.append("--no-webui")
if self.no_models_autoload: