prune: remove superseded/non-functional artifacts

README.md

@@ -69,8 +69,6 @@ entrypoint, `prefill`, with a static query width of 64
 | Path | Bytes | Context | Functions |
 |---|---:|---|---|
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | 3,989,986,858 | 4096 | main + prefill |
-| `ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | 3,989,986,830 | 8192 | main + prefill |
-| `ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` | 3,989,986,844 | 16384 | main + prefill |
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin` | 3,989,205,604 | 4096 | main — **does not load**, see Status |
 | `w4a8/gemma4_e4b_qat_decode_int4lin_a8_tbl_pf64` | 3,990,690,638 | 16384 | main + prefill |
 
@@ -79,12 +77,6 @@ Each folder holds `<name>.aimodel/` (`main.mlirb` ≈ 3.96 GB, `main.hash`, asse
 32,169,626 B, `tokenizer_config.json`, `generation_config.json`, `chat_template.jinja`
 18,569 B). The `w4a8` folder additionally ships its `calibration_corpus.jsonl` (35,045 B).
 
-**The three `_tbl_pf64` folders hold the same weights and the same graph.** `--max-ctx`
-changes exactly one thing: `language.max_context_length` in the bundle manifest. Function
-signatures, state descriptors and export peak RSS are identical at every value. Pick the
-folder whose manifest integer matches the window you intend to run; a context bump is a
-manifest edit, not a conversion.
-
 **Stop token:** every bundle declares `eos_token = "<turn|>"` (id 106), which is the turn
 terminator Gemma 4 emits. `generation_config.json` independently lists
 `eos_token_id: [1, 106, 50]`. A host that stops on the raw upstream `<eos>` instead will
@@ -209,8 +201,6 @@ reachable. 15k was not attempted.
 | Artifact | Status |
 |---|---|
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64` (ctx 4096) | **QUALIFIED FOR GUIDED GENERATION** — measured: 10/10 parse, 10/10 enum-clean, 14.70/5.93 s/row, 9.5–26.4 tok/s, 9.99 GB peak footprint. Not qualified for free-form generation on the current reference engine implementation. |
-| `ctx8192/…_tbl_pf64` | **QUALIFIED BY EQUIVALENCE** — same weights and graph, wider manifest integer. Free-form at this depth is measured-unsafe (31.33 GB under a 32-token cap). |
-| `ctx16384/…_tbl_pf64` | **QUALIFIED BY EQUIVALENCE** — as above; free-form at this depth was not attempted. |
 | `w4a8/gemma4_e4b_qat_decode_int4lin_a8_tbl_pf64` | **EXPERIMENTAL** — built, unmeasured. Gate: a Mac-side oracle/parity check plus a device benchmark. |
 | `gpu-pipelined/gemma4_e4b_qat_decode_int4lin` | **BLOCKED** — does not load on any current code path. |
 | `stable/…_tbl_pf64_stable_c16384` | **EXPERIMENTAL** — shape-stable decode contract; removes the per-token memory growth by design; requires host support for absolute-position inputs (in progress); no on-device measurements yet. |
@@ -292,7 +282,7 @@ resolves its cache strategy from the state descriptor will allocate the full cac
 front (0.50 GB for E2B, 1.61 GB for E4B) instead of growing it — that fixed cost is the
 trade for the unbounded growth it replaces.
 
-Unlike the `ctx*/` folders, the context ceiling here is **encoded in the graph**: a
+The context ceiling here is **encoded in the graph**: a
 different window needs a different export, not a manifest edit.
 
 **Verification.** Before conversion, the stable graph was checked against the shipped

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/main.hash

@@ -1 +0,0 @@
-�_���jhA�je, ���O
,F��9g�

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/main.mlirb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e25fbda5e46a6841856a652c208516e6f51d4f0c13010b142c46af90391067af
-size 3957793909

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/metadata.json

@@ -1,5 +0,0 @@
-{
-  "assetVersion" : "2.0",
-  "creationDate" : "20260817T204711Z",
-  "producer" : "coreai-core 1.0.0b2"
-}

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/metadata.json

@@ -1,29 +0,0 @@
-{
-  "metadata_version": "0.2",
-  "kind": "llm",
-  "name": "gemma4_e4b_qat_decode_int4lin_tbl_pf64",
-  "assets": {
-    "main": "gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel"
-  },
-  "language": {
-    "tokenizer": "google/gemma-4-E4B-it-qat-q4_0-unquantized",
-    "vocab_size": 262144,
-    "max_context_length": 16384,
-    "embedded_tokenizer": true,
-    "function_map": {
-      "main": [
-        "main",
-        "prefill"
-      ]
-    }
-  },
-  "source": {
-    "model_definition": "torch",
-    "hf_model_id": "google/gemma-4-E4B-it-qat-q4_0-unquantized"
-  },
-  "compression": null,
-  "compilation": {
-    "date": "2026-08-17T20:47:15.030070+00:00",
-    "targets": []
-  }
-}

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/chat_template.jinja

@@ -1,386 +0,0 @@
-{#
-  Template: Google Gemma 4 Canonical Chat Template
-  Author: Google Gemma Engineering Team
-  Published: 2026-07-09
-  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
-#}
-{%- macro format_parameters(properties, required, filter_keys=false) -%}
-    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
-    {%- set ns = namespace(found_first=false) -%}
-    {%- for key, value in properties | dictsort -%}
-        {%- set add_comma = false -%}
-        {%- if not filter_keys or key not in standard_keys -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {{ key }}:{
-            {%- if value['description'] -%}
-                description:<|"|>{{ value['description'] }}<|"|>
-                {%- set add_comma = true -%}
-            {%- endif -%}
-            {%- if value['type'] | upper == 'STRING' -%}
-                {%- if value['enum'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    enum:{{ format_argument(value['enum']) }}
-                {%- endif -%}
-            {%- elif value['type'] | upper == 'ARRAY' -%}
-                {%- if value['items'] is mapping and value['items'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    items:{
-                    {%- set ns_items = namespace(found_first=false) -%}
-                    {%- for item_key, item_value in value['items'] | dictsort -%}
-                        {%- if item_value is not none -%}
-                            {%- if ns_items.found_first %},{% endif -%}
-                            {%- set ns_items.found_first = true -%}
-                            {%- if item_key == 'properties' -%}
-                                properties:{
-                                {%- if item_value is mapping -%}
-                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
-                                {%- endif -%}
-                                }
-                            {%- elif item_key == 'required' -%}
-                                required:[
-                                {%- for req_item in item_value -%}
-                                    <|"|>{{- req_item -}}<|"|>
-                                    {%- if not loop.last %},{% endif -%}
-                                {%- endfor -%}
-                                ]
-                            {%- elif item_key == 'type' -%}
-                                {%- if item_value is string -%}
-                                    type:{{ format_argument(item_value | upper) }}
-                                {%- else -%}
-                                    type:{{ format_argument(item_value | map('upper') | list) }}
-                                {%- endif -%}
-                            {%- else -%}
-                                {{ item_key }}:{{ format_argument(item_value) }}
-                            {%- endif -%}
-                        {%- endif -%}
-                    {%- endfor -%}
-                    }
-                {%- endif -%}
-            {%- endif -%}
-            {%- if value['nullable'] %}
-                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                nullable:true
-            {%- endif -%}
-            {%- if value['type'] | upper == 'OBJECT' -%}
-                {%- if value['properties'] is defined and value['properties'] is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
-                    }
-                {%- elif value is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
-                    }
-                {%- endif -%}
-                {%- if value['required'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    required:[
-                    {%- for item in value['required'] | default([]) -%}
-                        <|"|>{{- item -}}<|"|>
-                        {%- if not loop.last %},{% endif -%}
-                    {%- endfor -%}
-                    ]
-                {%- endif -%}
-            {%- endif -%}
-            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-            type:<|"|>{{ value['type'] | upper }}<|"|>}
-        {%- endif -%}
-    {%- endfor -%}
-{%- endmacro -%}
-{%- macro format_function_declaration(tool_data) -%}
-    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
-    {%- set params = tool_data['function']['parameters'] -%}
-    {%- if params -%}
-        ,parameters:{
-        {%- if params['properties'] -%}
-            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
-        {%- endif -%}
-        {%- if params['required'] -%}
-            required:[
-            {%- for item in params['required'] -%}
-                <|"|>{{- item -}}<|"|>
-                {{- ',' if not loop.last -}}
-            {%- endfor -%}
-            ],
-        {%- endif -%}
-        {%- if params['type'] -%}
-            type:<|"|>{{- params['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    {%- if 'response' in tool_data['function'] -%}
-        {%- set response_declaration = tool_data['function']['response'] -%}
-        ,response:{
-        {%- if response_declaration['description'] -%}
-            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
-        {%- endif -%}
-        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
-            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    }
-{%- endmacro -%}
-{%- macro format_argument(argument, escape_keys=True) -%}
-    {%- if argument is none -%}
-        {{- 'null' -}}
-    {%- elif argument is string -%}
-        {{- '<|"|>' + argument + '<|"|>' -}}
-    {%- elif argument is boolean -%}
-        {{- 'true' if argument else 'false' -}}
-    {%- elif argument is mapping -%}
-        {{- '{' -}}
-        {%- set ns = namespace(found_first=false) -%}
-        {%- for key, value in argument | dictsort -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {%- if escape_keys -%}
-                {{- '<|"|>' + key + '<|"|>' -}}
-            {%- else -%}
-                {{- key -}}
-            {%- endif -%}
-            :{{- format_argument(value, escape_keys=escape_keys) -}}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- elif argument is sequence -%}
-        {{- '[' -}}
-        {%- for item in argument -%}
-            {{- format_argument(item, escape_keys=escape_keys) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- ']' -}}
-    {%- else -%}
-        {{- argument -}}
-    {%- endif -%}
-{%- endmacro -%}
-{%- macro strip_thinking(text) -%}
-    {%- set ns = namespace(result='') -%}
-    {%- for part in text.split('<channel|>') -%}
-        {%- if '<|channel>' in part -%}
-            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
-        {%- else -%}
-            {%- set ns.result = ns.result + part -%}
-        {%- endif -%}
-    {%- endfor -%}
-    {{- ns.result | trim -}}
-{%- endmacro -%}
-
-{%- macro format_tool_response_block(tool_name, response) -%}
-    {{- '<|tool_response>' -}}
-    {%- if response is mapping -%}
-        {{- 'response:' + tool_name + '{' -}}
-        {%- for key, value in response | dictsort -%}
-            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- else -%}
-        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
-    {%- endif -%}
-    {{- '<tool_response|>' -}}
-{%- endmacro -%}
-
-{#- ===== SETUP ===== -#}
-{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
-{%- set loop_messages = messages -%}
-{%- set enable_thinking = enable_thinking | default(false) -%}
-{%- set preserve_thinking = preserve_thinking | default(false) -%}
-{{- bos_token -}}
-{#- Handle System/Tool Definitions Block -#}
-{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
-    {{- '<|turn>system\n' -}}
-    {#- Inject Thinking token at the very top of the FIRST system turn -#}
-    {%- if enable_thinking -%}
-        {{- '<|think|>\n' -}}
-        {%- set ns.prev_message_type = 'think' -%}
-    {%- endif -%}
-    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
-        {%- if messages[0]['content'] is string -%}
-            {{- messages[0]['content'] | trim -}}
-        {%- elif messages[0]['content'] is sequence -%}
-            {%- for item in messages[0]['content'] -%}
-                {{- item['text'] | trim + ' '-}}
-            {%- endfor -%}
-        {%- endif -%}
-        {%- set loop_messages = messages[1:] -%}
-    {%- endif -%}
-    {%- if tools -%}
-        {%- for tool in tools %}
-            {{- '<|tool>' -}}
-            {{- format_function_declaration(tool) | trim -}}
-            {{- '<tool|>' -}}
-        {%- endfor %}
-        {%- set ns.prev_message_type = 'tool' -%}
-    {%- endif -%}
-    {{- '<turn|>\n' -}}
-{%- endif %}
-
-{#- Pre-scan: find last user message index for reasoning guard -#}
-{%- set ns_turn = namespace(last_user_idx=-1) -%}
-{%- for i in range(loop_messages | length) -%}
-    {%- if loop_messages[i]['role'] == 'user' -%}
-        {%- set ns_turn.last_user_idx = i -%}
-    {%- endif -%}
-{%- endfor -%}
-
-{#- Loop through messages -#}
-{%- for message in loop_messages -%}
-    {%- if message['role'] != 'tool' -%}
-    {%- set ns.prev_message_type = None -%}
-    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
-    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
-    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
-    {%- if not continue_same_model_turn -%}
-        {{- '<|turn>' + role + '\n' }}
-    {%- endif -%}
-
-    {#- Render reasoning/reasoning_content as thinking channel -#}
-    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
-    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
-    {%- if thinking_text and thinking_gate -%}
-        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
-    {%- endif -%}
-
-            {%- if message.get('tool_calls') -%}
-                {%- for tool_call in message.get('tool_calls') -%}
-                    {%- set function = tool_call['function'] -%}
-                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
-                    {%- if function['arguments'] is mapping -%}
-                        {%- set ns_args = namespace(found_first=false) -%}
-                        {%- for key, value in function['arguments'] | dictsort -%}
-                            {%- if ns_args.found_first %},{% endif -%}
-                            {%- set ns_args.found_first = true -%}
-                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-                        {%- endfor -%}
-                    {%- elif function['arguments'] is none -%}
-                    {%- else -%}
-                        {{- raise_exception(
-                            "chat_template: tool_calls[].function.arguments must be a "
-                            "JSON object (mapping), not a string. Deserialize arguments "
-                            "before passing to the template."
-                        ) -}}
-                    {%- endif -%}
-                    {{- '}<tool_call|>' -}}
-                {%- endfor -%}
-                {%- set ns.prev_message_type = 'tool_call' -%}
-            {%- endif -%}
-
-            {%- set ns_tr_out = namespace(flag=false) -%}
-            {%- if message.get('tool_responses') -%}
-                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
-                {%- for tool_response in message.get('tool_responses') -%}
-                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
-                    {%- set ns_tr_out.flag = true -%}
-                    {%- set ns.prev_message_type = 'tool_response' -%}
-                {%- endfor -%}
-            {%- elif message.get('tool_calls') -%}
-                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
-                {%- set ns_tool_scan = namespace(stopped=false) -%}
-                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
-                    {%- if ns_tool_scan.stopped -%}
-                    {%- elif loop_messages[k]['role'] != 'tool' -%}
-                        {%- set ns_tool_scan.stopped = true -%}
-                    {%- else -%}
-                        {%- set follow = loop_messages[k] -%}
-                        {#- Resolve tool_call_id to function name -#}
-                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
-                        {%- for tc in message.get('tool_calls') -%}
-                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
-                                {%- set ns_tname.name = tc['function']['name'] -%}
-                            {%- endif -%}
-                        {%- endfor -%}
-                        {#- Handle content as string or content-parts array -#}
-                        {%- set tool_body = follow.get('content') -%}
-                        {%- if tool_body is string -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- elif tool_body is sequence and tool_body is not string -%}
-                            {%- set ns_txt = namespace(s='') -%}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') == 'text' -%}
-                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
-                                {%- endif -%}
-                            {%- endfor -%}
-                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') in ['image', 'image_url'] -%}
-                                    {{- '<|image|>' -}}
-                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
-                                    {{- '<|audio|>' -}}
-                                {%- elif part.get('type') == 'video' -%}
-                                    {{- '<|video|>' -}}
-                                {%- endif -%}
-                            {%- endfor -%}
-                        {%- else -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- endif -%}
-                        {%- set ns_tr_out.flag = true -%}
-                        {%- set ns.prev_message_type = 'tool_response' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-
-            {%- set captured_content -%}
-            {%- if message.get('content') is string -%}
-                {%- if role == 'model' -%}
-                    {{- strip_thinking(message['content']) -}}
-                {%- else -%}
-                    {{- message['content'] | trim -}}
-                {%- endif -%}
-            {%- elif message.get('content') is sequence -%}
-                {%- for item in message['content'] -%}
-                    {%- if item.get('type') == 'text' -%}
-                        {%- if role == 'model' -%}
-                            {{- strip_thinking(item['text']) -}}
-                        {%- else -%}
-                            {{- item['text'] | trim -}}
-                        {%- endif -%}
-                    {%- elif item.get('type') in ['image', 'image_url'] -%}
-                        {{- '<|image|>' -}}
-                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
-                        {{- '<|audio|>' -}}
-                    {%- elif item.get('type') == 'video' -%}
-                        {{- '<|video|>' -}}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-            {%- endset -%}
-
-            {{- captured_content -}}
-            {%- set has_content = captured_content | trim | length > 0 -%}
-
-        {#- Forward-scan: find next non-tool message role for continuation detection -#}
-        {%- set next_nt = namespace(role=None, found=false) -%}
-        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
-            {%- if not next_nt.found -%}
-                {%- if loop_messages[j]['role'] != 'tool' -%}
-                    {%- set next_nt.role = loop_messages[j]['role'] -%}
-                    {%- set next_nt.found = true -%}
-                {%- endif -%}
-            {%- endif -%}
-        {%- endfor -%}
-
-        {%- set continues_into_next = (
-            role == 'model'
-            and next_nt.role == 'assistant'
-            and (not message.get('tool_calls') or ns_tr_out.flag)
-        ) -%}
-
-        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
-            {{- '<|tool_response>' -}}
-        {%- elif continues_into_next -%}
-        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
-            {{- '<turn|>\n' -}}
-        {%- endif -%}
-
-    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
-    {%- set ns.prev_non_tool_role = message['role'] -%}
-    {%- endif -%}
-{%- endfor -%}
-
-{%- if add_generation_prompt -%}
-    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
-        {{- '<|turn>model\n' -}}
-    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
-        {{- '<|channel>thought\n' -}}
-    {%- endif -%}
-{%- endif -%}

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/generation_config.json

@@ -1,14 +0,0 @@
-{
-  "bos_token_id": 2,
-  "do_sample": true,
-  "eos_token_id": [
-    1,
-    106,
-    50
-  ],
-  "pad_token_id": 0,
-  "temperature": 1.0,
-  "top_k": 64,
-  "top_p": 0.95,
-  "transformers_version": "5.6.2"
-}

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
-size 32169626

ctx16384/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/tokenizer_config.json

@@ -1,142 +0,0 @@
-{
-  "audio_token": "<|audio|>",
-  "backend": "tokenizers",
-  "boa_token": "<|audio>",
-  "boi_token": "<|image>",
-  "bos_token": "<bos>",
-  "eoa_token": "<audio|>",
-  "eoc_token": "<channel|>",
-  "eoi_token": "<image|>",
-  "eos_token": "<turn|>",
-  "eot_token": "<turn|>",
-  "escape_token": "<|\"|>",
-  "etc_token": "<tool_call|>",
-  "etd_token": "<tool|>",
-  "etr_token": "<tool_response|>",
-  "extra_special_tokens": [
-    "<|video|>"
-  ],
-  "image_token": "<|image|>",
-  "is_local": false,
-  "local_files_only": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "processor_class": "Gemma4Processor",
-  "response_schema": {
-    "properties": {
-      "content": {
-        "type": "string"
-      },
-      "role": {
-        "const": "assistant"
-      },
-      "thinking": {
-        "type": "string"
-      },
-      "tool_calls": {
-        "items": {
-          "properties": {
-            "function": {
-              "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
-                "name": {
-                  "type": "string"
-                }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
-            }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
-      }
-    },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
-  },
-  "response_template": {
-    "defaults": {
-      "role": "assistant"
-    },
-    "fields": {
-      "content": {
-        "close": [
-          "<turn|>",
-          "<|tool_response>",
-          "<eos>"
-        ],
-        "content": "text"
-      },
-      "thinking": {
-        "close": "<channel|>",
-        "content": "text",
-        "open": "<|channel>thought\n"
-      },
-      "tool_calls": {
-        "close": "<tool_call|>",
-        "content": "json",
-        "content_args": {
-          "string_delims": [
-            [
-              "<|\"|>",
-              "<|\"|>"
-            ]
-          ],
-          "unquoted_keys": true
-        },
-        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
-        "repeats": true,
-        "transform": {
-          "function": {
-            "arguments": "{content}",
-            "name": "{name}"
-          },
-          "type": "function"
-        }
-      }
-    },
-    "start_anchor": [
-      "<|turn>model\n",
-      "<tool_response|>"
-    ]
-  },
-  "soc_token": "<|channel>",
-  "sot_token": "<|turn>",
-  "stc_token": "<|tool_call>",
-  "std_token": "<|tool>",
-  "str_token": "<|tool_response>",
-  "think_token": "<|think|>",
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>"
-}

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/main.hash

@@ -1 +0,0 @@
-�S=�[a�6�39)�b+�o�P �\�!0��RWgT1

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/main.mlirb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ff533dea5b61e1369f333929aa622bf36f9a5020d55ca0213097ba5257675431
-size 3957793896

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel/metadata.json

@@ -1,5 +0,0 @@
-{
-  "assetVersion" : "2.0",
-  "creationDate" : "20260817T204459Z",
-  "producer" : "coreai-core 1.0.0b2"
-}

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/metadata.json

@@ -1,29 +0,0 @@
-{
-  "metadata_version": "0.2",
-  "kind": "llm",
-  "name": "gemma4_e4b_qat_decode_int4lin_tbl_pf64",
-  "assets": {
-    "main": "gemma4_e4b_qat_decode_int4lin_tbl_pf64.aimodel"
-  },
-  "language": {
-    "tokenizer": "google/gemma-4-E4B-it-qat-q4_0-unquantized",
-    "vocab_size": 262144,
-    "max_context_length": 8192,
-    "embedded_tokenizer": true,
-    "function_map": {
-      "main": [
-        "main",
-        "prefill"
-      ]
-    }
-  },
-  "source": {
-    "model_definition": "torch",
-    "hf_model_id": "google/gemma-4-E4B-it-qat-q4_0-unquantized"
-  },
-  "compression": null,
-  "compilation": {
-    "date": "2026-08-17T20:45:02.940360+00:00",
-    "targets": []
-  }
-}

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/chat_template.jinja

@@ -1,386 +0,0 @@
-{#
-  Template: Google Gemma 4 Canonical Chat Template
-  Author: Google Gemma Engineering Team
-  Published: 2026-07-09
-  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
-#}
-{%- macro format_parameters(properties, required, filter_keys=false) -%}
-    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
-    {%- set ns = namespace(found_first=false) -%}
-    {%- for key, value in properties | dictsort -%}
-        {%- set add_comma = false -%}
-        {%- if not filter_keys or key not in standard_keys -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {{ key }}:{
-            {%- if value['description'] -%}
-                description:<|"|>{{ value['description'] }}<|"|>
-                {%- set add_comma = true -%}
-            {%- endif -%}
-            {%- if value['type'] | upper == 'STRING' -%}
-                {%- if value['enum'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    enum:{{ format_argument(value['enum']) }}
-                {%- endif -%}
-            {%- elif value['type'] | upper == 'ARRAY' -%}
-                {%- if value['items'] is mapping and value['items'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    items:{
-                    {%- set ns_items = namespace(found_first=false) -%}
-                    {%- for item_key, item_value in value['items'] | dictsort -%}
-                        {%- if item_value is not none -%}
-                            {%- if ns_items.found_first %},{% endif -%}
-                            {%- set ns_items.found_first = true -%}
-                            {%- if item_key == 'properties' -%}
-                                properties:{
-                                {%- if item_value is mapping -%}
-                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
-                                {%- endif -%}
-                                }
-                            {%- elif item_key == 'required' -%}
-                                required:[
-                                {%- for req_item in item_value -%}
-                                    <|"|>{{- req_item -}}<|"|>
-                                    {%- if not loop.last %},{% endif -%}
-                                {%- endfor -%}
-                                ]
-                            {%- elif item_key == 'type' -%}
-                                {%- if item_value is string -%}
-                                    type:{{ format_argument(item_value | upper) }}
-                                {%- else -%}
-                                    type:{{ format_argument(item_value | map('upper') | list) }}
-                                {%- endif -%}
-                            {%- else -%}
-                                {{ item_key }}:{{ format_argument(item_value) }}
-                            {%- endif -%}
-                        {%- endif -%}
-                    {%- endfor -%}
-                    }
-                {%- endif -%}
-            {%- endif -%}
-            {%- if value['nullable'] %}
-                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                nullable:true
-            {%- endif -%}
-            {%- if value['type'] | upper == 'OBJECT' -%}
-                {%- if value['properties'] is defined and value['properties'] is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
-                    }
-                {%- elif value is mapping -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    properties:{
-                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
-                    }
-                {%- endif -%}
-                {%- if value['required'] -%}
-                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-                    required:[
-                    {%- for item in value['required'] | default([]) -%}
-                        <|"|>{{- item -}}<|"|>
-                        {%- if not loop.last %},{% endif -%}
-                    {%- endfor -%}
-                    ]
-                {%- endif -%}
-            {%- endif -%}
-            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
-            type:<|"|>{{ value['type'] | upper }}<|"|>}
-        {%- endif -%}
-    {%- endfor -%}
-{%- endmacro -%}
-{%- macro format_function_declaration(tool_data) -%}
-    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
-    {%- set params = tool_data['function']['parameters'] -%}
-    {%- if params -%}
-        ,parameters:{
-        {%- if params['properties'] -%}
-            properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
-        {%- endif -%}
-        {%- if params['required'] -%}
-            required:[
-            {%- for item in params['required'] -%}
-                <|"|>{{- item -}}<|"|>
-                {{- ',' if not loop.last -}}
-            {%- endfor -%}
-            ],
-        {%- endif -%}
-        {%- if params['type'] -%}
-            type:<|"|>{{- params['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    {%- if 'response' in tool_data['function'] -%}
-        {%- set response_declaration = tool_data['function']['response'] -%}
-        ,response:{
-        {%- if response_declaration['description'] -%}
-            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
-        {%- endif -%}
-        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
-            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
-        {%- endif -%}
-    {%- endif -%}
-    }
-{%- endmacro -%}
-{%- macro format_argument(argument, escape_keys=True) -%}
-    {%- if argument is none -%}
-        {{- 'null' -}}
-    {%- elif argument is string -%}
-        {{- '<|"|>' + argument + '<|"|>' -}}
-    {%- elif argument is boolean -%}
-        {{- 'true' if argument else 'false' -}}
-    {%- elif argument is mapping -%}
-        {{- '{' -}}
-        {%- set ns = namespace(found_first=false) -%}
-        {%- for key, value in argument | dictsort -%}
-            {%- if ns.found_first %},{% endif -%}
-            {%- set ns.found_first = true -%}
-            {%- if escape_keys -%}
-                {{- '<|"|>' + key + '<|"|>' -}}
-            {%- else -%}
-                {{- key -}}
-            {%- endif -%}
-            :{{- format_argument(value, escape_keys=escape_keys) -}}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- elif argument is sequence -%}
-        {{- '[' -}}
-        {%- for item in argument -%}
-            {{- format_argument(item, escape_keys=escape_keys) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- ']' -}}
-    {%- else -%}
-        {{- argument -}}
-    {%- endif -%}
-{%- endmacro -%}
-{%- macro strip_thinking(text) -%}
-    {%- set ns = namespace(result='') -%}
-    {%- for part in text.split('<channel|>') -%}
-        {%- if '<|channel>' in part -%}
-            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
-        {%- else -%}
-            {%- set ns.result = ns.result + part -%}
-        {%- endif -%}
-    {%- endfor -%}
-    {{- ns.result | trim -}}
-{%- endmacro -%}
-
-{%- macro format_tool_response_block(tool_name, response) -%}
-    {{- '<|tool_response>' -}}
-    {%- if response is mapping -%}
-        {{- 'response:' + tool_name + '{' -}}
-        {%- for key, value in response | dictsort -%}
-            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-            {%- if not loop.last %},{% endif -%}
-        {%- endfor -%}
-        {{- '}' -}}
-    {%- else -%}
-        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
-    {%- endif -%}
-    {{- '<tool_response|>' -}}
-{%- endmacro -%}
-
-{#- ===== SETUP ===== -#}
-{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
-{%- set loop_messages = messages -%}
-{%- set enable_thinking = enable_thinking | default(false) -%}
-{%- set preserve_thinking = preserve_thinking | default(false) -%}
-{{- bos_token -}}
-{#- Handle System/Tool Definitions Block -#}
-{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
-    {{- '<|turn>system\n' -}}
-    {#- Inject Thinking token at the very top of the FIRST system turn -#}
-    {%- if enable_thinking -%}
-        {{- '<|think|>\n' -}}
-        {%- set ns.prev_message_type = 'think' -%}
-    {%- endif -%}
-    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
-        {%- if messages[0]['content'] is string -%}
-            {{- messages[0]['content'] | trim -}}
-        {%- elif messages[0]['content'] is sequence -%}
-            {%- for item in messages[0]['content'] -%}
-                {{- item['text'] | trim + ' '-}}
-            {%- endfor -%}
-        {%- endif -%}
-        {%- set loop_messages = messages[1:] -%}
-    {%- endif -%}
-    {%- if tools -%}
-        {%- for tool in tools %}
-            {{- '<|tool>' -}}
-            {{- format_function_declaration(tool) | trim -}}
-            {{- '<tool|>' -}}
-        {%- endfor %}
-        {%- set ns.prev_message_type = 'tool' -%}
-    {%- endif -%}
-    {{- '<turn|>\n' -}}
-{%- endif %}
-
-{#- Pre-scan: find last user message index for reasoning guard -#}
-{%- set ns_turn = namespace(last_user_idx=-1) -%}
-{%- for i in range(loop_messages | length) -%}
-    {%- if loop_messages[i]['role'] == 'user' -%}
-        {%- set ns_turn.last_user_idx = i -%}
-    {%- endif -%}
-{%- endfor -%}
-
-{#- Loop through messages -#}
-{%- for message in loop_messages -%}
-    {%- if message['role'] != 'tool' -%}
-    {%- set ns.prev_message_type = None -%}
-    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
-    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
-    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
-    {%- if not continue_same_model_turn -%}
-        {{- '<|turn>' + role + '\n' }}
-    {%- endif -%}
-
-    {#- Render reasoning/reasoning_content as thinking channel -#}
-    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
-    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
-    {%- if thinking_text and thinking_gate -%}
-        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
-    {%- endif -%}
-
-            {%- if message.get('tool_calls') -%}
-                {%- for tool_call in message.get('tool_calls') -%}
-                    {%- set function = tool_call['function'] -%}
-                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
-                    {%- if function['arguments'] is mapping -%}
-                        {%- set ns_args = namespace(found_first=false) -%}
-                        {%- for key, value in function['arguments'] | dictsort -%}
-                            {%- if ns_args.found_first %},{% endif -%}
-                            {%- set ns_args.found_first = true -%}
-                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
-                        {%- endfor -%}
-                    {%- elif function['arguments'] is none -%}
-                    {%- else -%}
-                        {{- raise_exception(
-                            "chat_template: tool_calls[].function.arguments must be a "
-                            "JSON object (mapping), not a string. Deserialize arguments "
-                            "before passing to the template."
-                        ) -}}
-                    {%- endif -%}
-                    {{- '}<tool_call|>' -}}
-                {%- endfor -%}
-                {%- set ns.prev_message_type = 'tool_call' -%}
-            {%- endif -%}
-
-            {%- set ns_tr_out = namespace(flag=false) -%}
-            {%- if message.get('tool_responses') -%}
-                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
-                {%- for tool_response in message.get('tool_responses') -%}
-                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
-                    {%- set ns_tr_out.flag = true -%}
-                    {%- set ns.prev_message_type = 'tool_response' -%}
-                {%- endfor -%}
-            {%- elif message.get('tool_calls') -%}
-                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
-                {%- set ns_tool_scan = namespace(stopped=false) -%}
-                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
-                    {%- if ns_tool_scan.stopped -%}
-                    {%- elif loop_messages[k]['role'] != 'tool' -%}
-                        {%- set ns_tool_scan.stopped = true -%}
-                    {%- else -%}
-                        {%- set follow = loop_messages[k] -%}
-                        {#- Resolve tool_call_id to function name -#}
-                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
-                        {%- for tc in message.get('tool_calls') -%}
-                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
-                                {%- set ns_tname.name = tc['function']['name'] -%}
-                            {%- endif -%}
-                        {%- endfor -%}
-                        {#- Handle content as string or content-parts array -#}
-                        {%- set tool_body = follow.get('content') -%}
-                        {%- if tool_body is string -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- elif tool_body is sequence and tool_body is not string -%}
-                            {%- set ns_txt = namespace(s='') -%}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') == 'text' -%}
-                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
-                                {%- endif -%}
-                            {%- endfor -%}
-                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
-                            {%- for part in tool_body -%}
-                                {%- if part.get('type') in ['image', 'image_url'] -%}
-                                    {{- '<|image|>' -}}
-                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
-                                    {{- '<|audio|>' -}}
-                                {%- elif part.get('type') == 'video' -%}
-                                    {{- '<|video|>' -}}
-                                {%- endif -%}
-                            {%- endfor -%}
-                        {%- else -%}
-                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
-                        {%- endif -%}
-                        {%- set ns_tr_out.flag = true -%}
-                        {%- set ns.prev_message_type = 'tool_response' -%}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-
-            {%- set captured_content -%}
-            {%- if message.get('content') is string -%}
-                {%- if role == 'model' -%}
-                    {{- strip_thinking(message['content']) -}}
-                {%- else -%}
-                    {{- message['content'] | trim -}}
-                {%- endif -%}
-            {%- elif message.get('content') is sequence -%}
-                {%- for item in message['content'] -%}
-                    {%- if item.get('type') == 'text' -%}
-                        {%- if role == 'model' -%}
-                            {{- strip_thinking(item['text']) -}}
-                        {%- else -%}
-                            {{- item['text'] | trim -}}
-                        {%- endif -%}
-                    {%- elif item.get('type') in ['image', 'image_url'] -%}
-                        {{- '<|image|>' -}}
-                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
-                        {{- '<|audio|>' -}}
-                    {%- elif item.get('type') == 'video' -%}
-                        {{- '<|video|>' -}}
-                    {%- endif -%}
-                {%- endfor -%}
-            {%- endif -%}
-            {%- endset -%}
-
-            {{- captured_content -}}
-            {%- set has_content = captured_content | trim | length > 0 -%}
-
-        {#- Forward-scan: find next non-tool message role for continuation detection -#}
-        {%- set next_nt = namespace(role=None, found=false) -%}
-        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
-            {%- if not next_nt.found -%}
-                {%- if loop_messages[j]['role'] != 'tool' -%}
-                    {%- set next_nt.role = loop_messages[j]['role'] -%}
-                    {%- set next_nt.found = true -%}
-                {%- endif -%}
-            {%- endif -%}
-        {%- endfor -%}
-
-        {%- set continues_into_next = (
-            role == 'model'
-            and next_nt.role == 'assistant'
-            and (not message.get('tool_calls') or ns_tr_out.flag)
-        ) -%}
-
-        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
-            {{- '<|tool_response>' -}}
-        {%- elif continues_into_next -%}
-        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
-            {{- '<turn|>\n' -}}
-        {%- endif -%}
-
-    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
-    {%- set ns.prev_non_tool_role = message['role'] -%}
-    {%- endif -%}
-{%- endfor -%}
-
-{%- if add_generation_prompt -%}
-    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
-        {{- '<|turn>model\n' -}}
-    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
-        {{- '<|channel>thought\n' -}}
-    {%- endif -%}
-{%- endif -%}

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/generation_config.json

@@ -1,14 +0,0 @@
-{
-  "bos_token_id": 2,
-  "do_sample": true,
-  "eos_token_id": [
-    1,
-    106,
-    50
-  ],
-  "pad_token_id": 0,
-  "temperature": 1.0,
-  "top_k": 64,
-  "top_p": 0.95,
-  "transformers_version": "5.6.2"
-}

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
-size 32169626

ctx8192/gpu-pipelined/gemma4_e4b_qat_decode_int4lin_tbl_pf64/tokenizer/tokenizer_config.json

@@ -1,142 +0,0 @@
-{
-  "audio_token": "<|audio|>",
-  "backend": "tokenizers",
-  "boa_token": "<|audio>",
-  "boi_token": "<|image>",
-  "bos_token": "<bos>",
-  "eoa_token": "<audio|>",
-  "eoc_token": "<channel|>",
-  "eoi_token": "<image|>",
-  "eos_token": "<turn|>",
-  "eot_token": "<turn|>",
-  "escape_token": "<|\"|>",
-  "etc_token": "<tool_call|>",
-  "etd_token": "<tool|>",
-  "etr_token": "<tool_response|>",
-  "extra_special_tokens": [
-    "<|video|>"
-  ],
-  "image_token": "<|image|>",
-  "is_local": false,
-  "local_files_only": false,
-  "mask_token": "<mask>",
-  "model_max_length": 1000000000000000019884624838656,
-  "model_specific_special_tokens": {
-    "audio_token": "<|audio|>",
-    "boa_token": "<|audio>",
-    "boi_token": "<|image>",
-    "eoa_token": "<audio|>",
-    "eoc_token": "<channel|>",
-    "eoi_token": "<image|>",
-    "eot_token": "<turn|>",
-    "escape_token": "<|\"|>",
-    "etc_token": "<tool_call|>",
-    "etd_token": "<tool|>",
-    "etr_token": "<tool_response|>",
-    "image_token": "<|image|>",
-    "soc_token": "<|channel>",
-    "sot_token": "<|turn>",
-    "stc_token": "<|tool_call>",
-    "std_token": "<|tool>",
-    "str_token": "<|tool_response>",
-    "think_token": "<|think|>"
-  },
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "processor_class": "Gemma4Processor",
-  "response_schema": {
-    "properties": {
-      "content": {
-        "type": "string"
-      },
-      "role": {
-        "const": "assistant"
-      },
-      "thinking": {
-        "type": "string"
-      },
-      "tool_calls": {
-        "items": {
-          "properties": {
-            "function": {
-              "properties": {
-                "arguments": {
-                  "additionalProperties": {},
-                  "type": "object",
-                  "x-parser": "gemma4-tool-call"
-                },
-                "name": {
-                  "type": "string"
-                }
-              },
-              "type": "object",
-              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
-            },
-            "type": {
-              "const": "function"
-            }
-          },
-          "type": "object"
-        },
-        "type": "array",
-        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
-      }
-    },
-    "type": "object",
-    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
-  },
-  "response_template": {
-    "defaults": {
-      "role": "assistant"
-    },
-    "fields": {
-      "content": {
-        "close": [
-          "<turn|>",
-          "<|tool_response>",
-          "<eos>"
-        ],
-        "content": "text"
-      },
-      "thinking": {
-        "close": "<channel|>",
-        "content": "text",
-        "open": "<|channel>thought\n"
-      },
-      "tool_calls": {
-        "close": "<tool_call|>",
-        "content": "json",
-        "content_args": {
-          "string_delims": [
-            [
-              "<|\"|>",
-              "<|\"|>"
-            ]
-          ],
-          "unquoted_keys": true
-        },
-        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
-        "repeats": true,
-        "transform": {
-          "function": {
-            "arguments": "{content}",
-            "name": "{name}"
-          },
-          "type": "function"
-        }
-      }
-    },
-    "start_anchor": [
-      "<|turn>model\n",
-      "<tool_response|>"
-    ]
-  },
-  "soc_token": "<|channel>",
-  "sot_token": "<|turn>",
-  "stc_token": "<|tool_call>",
-  "std_token": "<|tool>",
-  "str_token": "<|tool_response>",
-  "think_token": "<|think|>",
-  "tokenizer_class": "GemmaTokenizer",
-  "unk_token": "<unk>"
-}