EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Revert "drop ascend scheduler" (#4580)

Browse Source 
Reverts vllm-project/vllm-ascend#4498
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
This commit is contained in:
Mengqing Cao
2025-11-29 22:20:48 +08:00
committed by GitHub
parent 4dbe4fd123
commit 517fd9272d
52 changed files with 2948 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/e2e/nightly/multi_node/config/models/DeepSeek-R1-W8A8-A2.yaml
View File

@@ -31,7 +31,7 @@ deployment:
--gpu-memory-utilization 0.9
--enforce-eager
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
--additional-config '{"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
--additional-config '{"ascend_scheduler_config":{"enabled":false},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
-
server_cmd: >
@@ -53,5 +53,5 @@ deployment:
--gpu-memory-utilization 0.9
--enforce-eager
--speculative-config '{"num_speculative_tokens": 1, "method":"deepseek_mtp"}'
--additional-config '{"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
--additional-config '{"ascend_scheduler_config":{"enabled":false},"chunked_prefill_for_mla":true,"enable_weight_nz_layout":true}'
benchmarks: