haylan/LLM-Server
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(models): correct DFlash2 Q8_0 drafter download URL

Browse Source 
The URL used the filename as the Hugging Face repo name. Also align
the compose fallback for LLAMA_DRAFT_MODEL_FILE with Q8_0.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
haylanandClaude Bot committed 2026-10-31 17:01:27 +01:00
1 parent e4febb5beb
commit 7d142ed59d
2 files changed
+2 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker-compose.yml
+1 -1
View File
@@ -29,7 +29,7 @@ services:
--cache-type-v q8_0 --cache-type-v q8_0
--cache-ram ${LLAMA_CACHE_RAM:-24576} --cache-ram ${LLAMA_CACHE_RAM:-24576}
--spec-type draft-dflash --spec-type draft-dflash
-md /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q4_K_M.gguf} -md /models/${LLAMA_DRAFT_MODEL_FILE:-Qwen3.8-27B-DFlash2-Q8_0.gguf}
--spec-draft-n-max ${LLAMA_SPEC_N_MAX:-7} --spec-draft-n-max ${LLAMA_SPEC_N_MAX:-7}
--jinja --jinja
# see docs/architecture.md#llama-server (flags), docs/network-access.md#backends (no host port) # see docs/architecture.md#llama-server (flags), docs/network-access.md#backends (no host port)
models.yml
+1 -1
View File
@@ -4,4 +4,4 @@ models:
- file: Qwen3.8-27B-UD-Q4_K_XL.gguf - file: Qwen3.8-27B-UD-Q4_K_XL.gguf
url: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.gguf url: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/Qwen3.8-27B-UD-Q4_K_XL.gguf
- file: Qwen3.8-27B-DFlash2-Q8_0.gguf - file: Qwen3.8-27B-DFlash2-Q8_0.gguf
url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-Q8_0.gguf/resolve/main/Qwen3.8-27B-DFlash2-Q8_0.gguf url: https://huggingface.co/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/main/Qwen3.8-27B-DFlash2-Q8_0.gguf