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

upgrade vLLM to main (#4608)

Browse Source 
1. fix https://github.com/vllm-project/vllm/pull/28542
The model structure modifications we involved in are:
     - Qwen2.5-VL(still exist some patch)
     - Qwen2-VL
     - Qwen2
     - DeepSeek series
     - Qwen-moe series
2. fix https://github.com/vllm-project/vllm/pull/29121
   the output token now  type changed from np to `list[list[int]]`

3. fix https://github.com/vllm-project/vllm/pull/29262
    `xformers` backend for multimodal now has been deprecated
4. fix https://github.com/vllm-project/vllm/pull/29342

5. fix https://github.com/vllm-project/vllm/pull/28579
6. fix https://github.com/vllm-project/vllm/pull/28718
7. fix https://github.com/vllm-project/vllm/issues/28665
8. fix https://github.com/vllm-project/vllm/pull/26847
vllm introduced the `optimization-level`, some default config has been
changed, and the param `--enforce-eager` has been deprecated
9. fix http://github.com/vllm-project/vllm/pull/29223 it retuns tuple
for sampler.
10. fix https://github.com/vllm-project/vllm/pull/29471 we'll remove the
related patch to avoid this kind of error.

Co-authored-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: wangli <wangli858794774@gmail.com>


- vLLM version: v0.11.2

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Co-authored-by: wangli <wangli858794774@gmail.com>
Co-authored-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
wangxiyuan
2025-12-02 22:10:52 +08:00
committed by GitHub
parent 4588cdac02
commit 7f2673ea2d
60 changed files with 383 additions and 374 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/core/recompute_scheduler.py
View File

@@ -456,7 +456,7 @@ class RecomputeScheduler(SchedulerInterface):
# chunked prefill has to be enabled explicitly to allow
# pooling requests to be chunked
if not self.scheduler_config.chunked_prefill_enabled and \
if not self.scheduler_config.enable_chunked_prefill and \
num_new_tokens > token_budget:
self.waiting.pop_request()
skipped_waiting_requests.prepend_request(request)

4
vllm_ascend/core/scheduler.py
View File

@@ -70,7 +70,7 @@ class AscendScheduler(Scheduler):
self._initialize_common()
def schedule(self) -> SchedulerOutput:
if self.scheduler_config.chunked_prefill_enabled:
if self.scheduler_config.enable_chunked_prefill:
return super().schedule()
scheduled_new_reqs: list[Request] = []
scheduled_resumed_reqs: list[Request] = []
@@ -534,7 +534,7 @@ class AscendScheduler(Scheduler):
return True
def _get_prompt_limit(self, request: Request) -> int:
if (self.scheduler_config.chunked_prefill_enabled
if (self.scheduler_config.enable_chunked_prefill
and not self.scheduler_config.is_multi_step):
prompt_limit = self.vllm_config.model_config.max_model_len
else:

2
vllm_ascend/core/scheduler_dynamic_batch.py
View File

@@ -404,7 +404,7 @@ class SchedulerDynamicBatch(Scheduler):
# chunked prefill has to be enabled explicitly to allow
# pooling requests to be chunked
if not self.scheduler_config.chunked_prefill_enabled and \
if not self.scheduler_config.enable_chunked_prefill and \
num_new_tokens > token_budget:
self.waiting.pop_request()
skipped_waiting_requests.prepend_request(request)