sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests Actions 168 Packages Projects Releases Wiki Activity

spec : refactor params (#22397)

Browse Source 
* spec : refactor params

* cont : fix

* cont : rename "sparam" to "sampling"

* cont : add spec params category

* cont : add info about removed arguments

* cont : skip param length check for spec params

* cont : adapt server tests
This commit is contained in:
Georgi Gerganov
2026-04-28 09:07:33 +03:00
committed by GitHub
parent 516e8d7a8a
commit 14e733e36f
18 changed files with 661 additions and 409 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: