[KV Cache] GLM-5.3-Flash: use the generic packed KV layout; CircularBufferSpec tail with speculative ring slots (#57169)
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai> Signed-off-by: Dakai An <dakaian108@gmail.com> Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
This commit is contained in:
co-authored by
Yifan Qiao
OpenAI Codex
OpenAI Codex
Lucas Wilkinson
Claude Opus 5.5
Lucas Wilkinson
parent
3766a67a32
commit
02e55d2af3
@@ -688,7 +688,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
max_num_batched_tokens=self.max_num_tokens,
|
||||
max_num_blocks_per_group=max_num_blocks_per_group,
|
||||
device=self.device,
|
||||
kernel_block_sizes=self.kernel_block_sizes,
|
||||
slot_mapping_enabled=slot_mapping_enabled,
|
||||
dcp_sharded=dcp_sharded,
|
||||
cp_size=self.dcp_size,
|
||||
@@ -773,6 +772,13 @@ class GPUModelRunner(LoRAModelRunnerMixin):
|
||||
self.vllm_config,
|
||||
kv_cache_allocation_context=kv_cache_allocation_context,
|
||||
block_tables=self.block_tables,
|
||||
# Draft groups build their own metadata, so they map the views too.
|
||||
attn_groups=(
|
||||
g
|
||||
for groups in self.attn_groups
|
||||
+ getattr(self.speculator, "attn_groups", [])
|
||||
for g in groups
|
||||
),
|
||||
)
|
||||
self.kv_caches = [
|
||||
cache for cache in kv_caches_dict.values() if cache.device == self.device
|
||||
|
||||
Reference in New Issue
Block a user